Biplab Banerjee

Mainak Singha, Harsh Pal, Ankit Jha et al.

Although deep learning models have shown impressive performance on supervised learning tasks, they often struggle to generalize well when the training (source) and test (target) domains differ. Unsupervised domain adaptation (DA) has emerged as a popular solution to this problem. However, current DA techniques rely on visual backbones, which may lack semantic richness. Despite the potential of large-scale vision-language foundation models like CLIP, their effectiveness for DA has yet to be fully explored. To address this gap, we introduce \textsc{AD-CLIP}, a domain-agnostic prompt learning strategy for CLIP that aims to solve the DA problem in the prompt space. We leverage the frozen vision backbone of CLIP to extract both image style (domain) and content information, which we apply to learn prompt tokens. Our prompts are designed to be domain-invariant and class-generalizable, by conditioning prompt learning on image style and content features simultaneously. We use standard supervised contrastive learning in the source domain, while proposing an entropy minimization strategy to align domains in the embedding space given the target domain data. We also consider a scenario where only target domain samples are available during testing, without any source domain data, and propose a cross-domain style mapping network to hallucinate domain-agnostic tokens. Our extensive experiments on three benchmark DA datasets demonstrate the effectiveness of \textsc{AD-CLIP} compared to existing literature. Code is available at \url{https://github.com/mainaksingha01/AD-CLIP}

Mainak Singha, Ankit Jha, Bhupendra Solanki et al.

In recent years, the success of large-scale vision-language models (VLMs) such as CLIP has led to their increased usage in various computer vision tasks. These models enable zero-shot inference through carefully crafted instructional text prompts without task-specific supervision. However, the potential of VLMs for generalization tasks in remote sensing (RS) has not been fully realized. To address this research gap, we propose a novel image-conditioned prompt learning strategy called the Visual Attention Parameterized Prompts Learning Network (APPLeNet). APPLeNet emphasizes the importance of multi-scale feature learning in RS scene classification and disentangles visual style and content primitives for domain generalization tasks. To achieve this, APPLeNet combines visual content features obtained from different layers of the vision encoder and style properties obtained from feature statistics of domain-specific batches. An attention-driven injection module is further introduced to generate visual tokens from this information. We also introduce an anti-correlation regularizer to ensure discrimination among the token embeddings, as this visual information is combined with the textual tokens. To validate APPLeNet, we curated four available RS benchmarks and introduced experimental protocols and datasets for three domain generalization tasks. Our results consistently outperform the relevant literature and code is available at https://github.com/mainaksingha01/APPLeNet

Md Aminur Hossain, Ayush V. Patel, Nitant Dube et al.

Cross-modal remote sensing image retrieval aims to retrieve semantically related scenes across heterogeneous sensing modalities. This remains challenging because paired observations may differ substantially in imaging physics, spatial resolution, spectral configuration, and visual appearance. Moreover, a single retrieval projection trained with one objective may be insufficient to jointly support cross-modal semantic alignment and same-modal neighbourhood preservation. We propose CR-JEPA, a Cross-modal Retrieval Joint-Embedding Predictive Architecture for dual-modality remote sensing retrieval. The model uses modality-specific stems, a shared transformer trunk, and JEPA-style predictive objectives to estimate masked latent target features within and across modalities. Inspired by LeJEPA, we apply Sketched Isotropic Gaussian Regularization to raw retrieval projections to stabilize embeddings and mitigate collapse. CR-JEPA further employs a decoupled-head design with a unified retrieval head for same-modal retrieval and a cross-modal retrieval head for cross-modal search. We evaluate CR-JEPA on BEN-14K, CBRSIR_VS, and DSRSID. On BEN-14K, CR-JEPA improves S1 to S2 retrieval from 61.23% to 75.82% and S2 to S1 retrieval from 63.73% to 75.40% over X-JEPA, while also achieving competitive same-modal retrieval with fewer parameters.

Mainak Singha, Ankit Jha, Biplab Banerjee

Large-scale foundation models, such as CLIP, have demonstrated remarkable success in visual recognition tasks by embedding images in a semantically rich space. Self-supervised learning (SSL) has also shown promise in improving visual recognition by learning invariant features. However, the combination of CLIP with SSL is found to face challenges due to the multi-task framework that blends CLIP's contrastive loss and SSL's loss, including difficulties with loss weighting and inconsistency among different views of images in CLIP's output space. To overcome these challenges, we propose a prompt learning-based model called GOPro, which is a unified framework that ensures similarity between various augmented views of input images in a shared image-text embedding space, using a pair of learnable image and text projectors atop CLIP, to promote invariance and generalizability. To automatically learn such prompts, we leverage the visual content and style primitives extracted from pre-trained CLIP and adapt them to the target task. In addition to CLIP's cross-domain contrastive loss, we introduce a visual contrastive loss and a novel prompt consistency loss, considering the different views of the images. GOPro is trained end-to-end on all three loss objectives, combining the strengths of CLIP and SSL in a principled manner. Empirical evaluations demonstrate that GOPro outperforms the state-of-the-art prompting techniques on three challenging domain generalization tasks across multiple benchmarks by a significant margin. Our code is available at https://github.com/mainaksingha01/GOPro.

Shirsha Bose, Ankit Jha, Enrico Fini et al.

Large-scale foundation models, such as CLIP, have demonstrated impressive zero-shot generalization performance on downstream tasks, leveraging well-designed language prompts. However, these prompt learning techniques often struggle with domain shift, limiting their generalization capabilities. In our study, we tackle this issue by proposing StyLIP, a novel approach for Domain Generalization (DG) that enhances CLIP's classification performance across domains. Our method focuses on a domain-agnostic prompt learning strategy, aiming to disentangle the visual style and content information embedded in CLIP's pre-trained vision encoder, enabling effortless adaptation to novel domains during inference. To achieve this, we introduce a set of style projectors that directly learn the domain-specific prompt tokens from the extracted multi-scale style features. These generated prompt embeddings are subsequently combined with the multi-scale visual content features learned by a content projector. The projectors are trained in a contrastive manner, utilizing CLIP's fixed vision and text backbones. Through extensive experiments conducted in five different DG settings on multiple benchmark datasets, we consistently demonstrate that StyLIP outperforms the current state-of-the-art (SOTA) methods.

Munish Monga, Sachin Kumar Giroh, Ankit Jha et al.

Multi-Target Domain Adaptation (MTDA) entails learning domain-invariant information from a single source domain and applying it to multiple unlabeled target domains. Yet, existing MTDA methods predominantly focus on addressing domain shifts within visual features, often overlooking semantic features and struggling to handle unknown classes, resulting in what is known as Open-Set (OS) MTDA. While large-scale vision-language foundation models like CLIP show promise, their potential for MTDA remains largely unexplored. This paper introduces COSMo, a novel method that learns domain-agnostic prompts through source domain-guided prompt learning to tackle the MTDA problem in the prompt space. By leveraging a domain-specific bias network and separate prompts for known and unknown classes, COSMo effectively adapts across domain and class shifts. To the best of our knowledge, COSMo is the first method to address Open-Set Multi-Target DA (OSMTDA), offering a more realistic representation of real-world scenarios and addressing the challenges of both open-set and multi-target DA. COSMo demonstrates an average improvement of $5.1\%$ across three challenging datasets: Mini-DomainNet, Office-31, and Office-Home, compared to other related DA methods adapted to operate within the OSMTDA setting. Code is available at: https://github.com/munish30monga/COSMo

Ankit Jha, Debabrata Pal, Mainak Singha et al. · deepmind

Recognition of remote sensing (RS) or aerial images is currently of great interest, and advancements in deep learning algorithms added flavor to it in recent years. Occlusion, intra-class variance, lighting, etc., might arise while training neural networks using unimodal RS visual input. Even though joint training of audio-visual modalities improves classification performance in a low-data regime, it has yet to be thoroughly investigated in the RS domain. Here, we aim to solve a novel problem where both the audio and visual modalities are present during the meta-training of a few-shot learning (FSL) classifier; however, one of the modalities might be missing during the meta-testing stage. This problem formulation is pertinent in the RS domain, given the difficulties in data acquisition or sensor malfunctioning. To mitigate, we propose a novel few-shot generative framework, Hallucinated Audio-Visual Embeddings-Network (HAVE-Net), to meta-train cross-modal features from limited unimodal data. Precisely, these hallucinated features are meta-learned from base classes and used for few-shot classification on novel classes during the inference phase. The experimental results on the benchmark ADVANCE and AudioSetZSL datasets show that our hallucinated modality augmentation strategy for few-shot classification outperforms the classifier performance trained with the real multimodal information at least by 0.8-2%.

Shirsha Bose, Ritesh Sur Chowdhury, Debabrata Pal et al.

Efficient road and building footprint extraction from satellite images are predominant in many remote sensing applications. However, precise segmentation map extraction is quite challenging due to the diverse building structures camouflaged by trees, similar spectral responses between the roads and buildings, and occlusions by heterogeneous traffic over the roads. Existing convolutional neural network (CNN)-based methods focus on either enriched spatial semantics learning for the building extraction or the fine-grained road topology extraction. The profound semantic information loss due to the traditional pooling mechanisms in CNN generates fragmented and disconnected road maps and poorly segmented boundaries for the densely spaced small buildings in complex surroundings. In this paper, we propose a novel attention-aware segmentation framework, Multi-Scale Supervised Dilated Multiple-Path Attention Network (MSSDMPA-Net), equipped with two new modules Dynamic Attention Map Guided Index Pooling (DAMIP) and Dynamic Attention Map Guided Spatial and Channel Attention (DAMSCA) to precisely extract the building footprints and road maps from remotely sensed images. DAMIP mines the salient features by employing a novel index pooling mechanism to retain important geometric information. On the other hand, DAMSCA simultaneously extracts the multi-scale spatial and spectral features. Besides, using dilated convolution and multi-scale deep supervision in optimizing MSSDMPA-Net helps achieve stellar performance. Experimental results over multiple benchmark building and road extraction datasets, ensures MSSDMPA-Net as the state-of-the-art (SOTA) method for building and road extraction.

Mainak Singha, Tanisha Gupta, Ankit Jha et al.

Pretrained biomedical vision-language models (VLMs) such as BioMedCLIP perform well on average but often degrade on challenging modalities where inter-class margins are small and acquisition-specific variations are pronounced, especially under few-shot supervision and when modality priors differ from pretraining corpora substantially. We propose BioVLM, a prompt-learning framework that improves cross-domain generalization without extensive backbone fine-tuning. BioVLM learns a diverse prompt bank and introduces dynamic prompt selection: for each input, it selects the most discriminative prompts via a low-entropy criterion on the predictive distribution, effectively coupling sparse few-shot evidence with rich LLM semantic priors. To strengthen this coupling, we distill high-confidence LLM-derived attributes and enforce robust knowledge transfer through strong/weak augmentation consistency. At test time, BioVLM adapts by choosing modality-appropriate prompts, enabling transfer to unseen categories and domains, while keeping training lightweight and inference efficient. On 11 MedMNIST+ 2D datasets, BioVLM achieves new state of the art across three distinct generalization settings. Codes are available at https://github.com/mainaksingha01/BioVLM.

Md Aminur Hossain, Ayush V. Patel, Sanjay K. Singh et al.

We introduce HQ-JEPA, a hybrid quantum-classical joint-embedding predictive architecture for cross-modal remote sensing representation learning. The proposed framework extends JEPA-style masked latent prediction to paired Sentinel-1 and Sentinel-2 imagery by predicting masked target representations from visible context regions while aligning heterogeneous modality features in a shared embedding space. To improve representation quality, HQ-JEPA combines four complementary objectives: latent token prediction, cross-modal token alignment, SIGReg-based Gaussian regularization in the fused latent space, and a differentiable SWAP-test-based Fidelity Quantum Similarity (FQS) loss. Unlike pixel reconstruction methods, HQ-JEPA learns semantic representations directly in latent space and uses quantum state-overlap-based similarity as an additional regularization signal. We evaluate the pretrained encoder on GeoBench classification and segmentation tasks under linear probing and fine-tuning settings. Results show that HQ-JEPA achieves competitive and often superior performance over strong self-supervised and remote sensing foundation-model baselines, demonstrating the benefit of integrating predictive self-supervision, cross-modal geometric regularization, and quantum fidelity-based representation learning for remote sensing applications.

Sandika Biswas, Kejie Li, Biplab Banerjee et al.

Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image. The existing research mainly proposes optimization-based approaches for reconstructing the scene from a sequence of RGB frames with explicitly defined physical laws and constraints between different scene elements (humans and objects). However, it is hard to explicitly define and model every physical law in every scenario. This paper proposes using an implicit feature representation of the scene elements to distinguish a physically plausible alignment of humans and objects from an implausible one. We propose using a graph-based holistic representation with an encoded physical representation of the scene to analyze the human-object and object-object interactions within the scene. Using this graphical representation, we adversarially train our model to learn the feasible alignments of the scene elements from the training data itself without explicitly defining the laws and constraints between them. Unlike the existing inference-time optimization-based approaches, we use this adversarially trained model to produce a per-frame 3D reconstruction of the scene that abides by the physical laws and constraints. Our learning-based method achieves comparable 3D reconstruction quality to existing optimization-based holistic human-scene reconstruction methods and does not need inference time optimization. This makes it better suited when compared to existing methods, for potential use in robotic applications, such as robot navigation, etc.

Sanchar Palit, Biplab Banerjee, Subhasis Chaudhuri

Scarcity of data and incremental learning of new tasks pose two major bottlenecks for many modern computer vision algorithms. The phenomenon of catastrophic forgetting, i.e., the model's inability to classify previously learned data after training with new batches of data, is a major challenge. Conventional methods address catastrophic forgetting while compromising the current session's training. Generative replay-based approaches, such as generative adversarial networks (GANs), have been proposed to mitigate catastrophic forgetting, but training GANs with few samples may lead to instability. To address these challenges, we propose a novel method that improves classification robustness by identifying a better embedding space using an improved contrasting loss. Our approach retains previously acquired knowledge in the embedding space, even when trained with new classes, by updating previous session class prototypes to represent the true class mean, which is crucial for our nearest class mean classification strategy. We demonstrate the effectiveness of our method by showing that the embedding space remains intact after training the model with new classes and outperforms existing state-of-the-art algorithms in terms of accuracy across different sessions.

Mohit Jaiswal, Naman Jain, Shivani Pathak et al.

Few-shot remote sensing image classification is challenging due to limited labeled samples and high variability in land-cover types. We propose a reconstruction-guided few-shot network (RGFS-Net) that enhances generalization to unseen classes while preserving consistency for seen categories. Our method incorporates a masked image reconstruction task, where parts of the input are occluded and reconstructed to encourage semantically rich feature learning. This auxiliary task strengthens spatial understanding and improves class discrimination under low-data settings. We evaluated the efficacy of EuroSAT and PatternNet datasets under 1-shot and 5-shot protocols, our approach consistently outperforms existing baselines. The proposed method is simple, effective, and compatible with standard backbones, offering a robust solution for few-shot remote sensing classification. Codes are available at https://github.com/stark0908/RGFS.

Prachet Dev Singh, Shyamsundar Paramasivam, Sneha Barman et al.

Hyperspectral image (HSI) classification presents unique challenges due to its high spectral dimensionality and limited labeled data. Traditional deep learning models often suffer from overfitting and high computational costs. Self-distillation (SD), a variant of knowledge distillation where a network learns from its own predictions, has recently emerged as a promising strategy to enhance model performance without requiring external teacher networks. In this work, we explore the application of SD to HSI by treating earlier outputs as soft targets, thereby enforcing consistency between intermediate and final predictions. This process improves intra-class compactness and inter-class separability in the learned feature space. Our approach is validated on two benchmark HSI datasets and demonstrates significant improvements in classification accuracy and robustness, highlighting the effectiveness of SD for spectral-spatial learning. Codes are available at https://github.com/Prachet-Dev-Singh/SDHSI.

Aditya Chaudhary, Sneha Barman, Mainak Singha et al.

In this paper, we propose a novel multimodal framework, Multimodal Language-Guided Network (MMLGNet), to align heterogeneous remote sensing modalities like Hyperspectral Imaging (HSI) and LiDAR with natural language semantics using vision-language models such as CLIP. With the increasing availability of multimodal Earth observation data, there is a growing need for methods that effectively fuse spectral, spatial, and geometric information while enabling semantic-level understanding. MMLGNet employs modality-specific encoders and aligns visual features with handcrafted textual embeddings in a shared latent space via bi-directional contrastive learning. Inspired by CLIP's training paradigm, our approach bridges the gap between high-dimensional remote sensing data and language-guided interpretation. Notably, MMLGNet achieves strong performance with simple CNN-based encoders, outperforming several established multimodal visual-only methods on two benchmark datasets, demonstrating the significant benefit of language supervision. Codes are available at https://github.com/AdityaChaudhary2913/CLIP_HSI.

Izzeddin Teeti, Rongali Sai Bhargav, Vivek Singh et al.

The emerging field of action prediction plays a vital role in various computer vision applications such as autonomous driving, activity analysis and human-computer interaction. Despite significant advancements, accurately predicting future actions remains a challenging problem due to high dimensionality, complex dynamics and uncertainties inherent in video data. Traditional supervised approaches require large amounts of labelled data, which is expensive and time-consuming to obtain. This paper introduces a novel self-supervised video strategy for enhancing action prediction inspired by DINO (self-distillation with no labels). The Temporal-DINO approach employs two models; a 'student' processing past frames; and a 'teacher' processing both past and future frames, enabling a broader temporal context. During training, the teacher guides the student to learn future context by only observing past frames. The strategy is evaluated on ROAD dataset for the action prediction downstream task using 3D-ResNet, Transformer, and LSTM architectures. The experimental results showcase significant improvements in prediction performance across these architectures, with our method achieving an average enhancement of 9.9% Precision Points (PP), highlighting its effectiveness in enhancing the backbones' capabilities of capturing long-term dependencies. Furthermore, our approach demonstrates efficiency regarding the pretraining dataset size and the number of epochs required. This method overcomes limitations present in other approaches, including considering various backbone architectures, addressing multiple prediction horizons, reducing reliance on hand-crafted augmentations, and streamlining the pretraining process into a single stage. These findings highlight the potential of our approach in diverse video-based tasks such as activity recognition, motion planning, and scene understanding.

Mainak Singha, Sarthak Mehrotra, Paolo Casari et al.

Recent vision-language models (VLMs) such as CLIP demonstrate impressive cross-modal reasoning, extending beyond images to 3D perception. Yet, these models remain fragile under domain shifts, especially when adapting from synthetic to real-world point clouds. Conventional 3D domain adaptation approaches rely on heavy trainable encoders, yielding strong accuracy but at the cost of efficiency. We introduce CLIPoint3D, the first framework for few-shot unsupervised 3D point cloud domain adaptation built upon CLIP. Our approach projects 3D samples into multiple depth maps and exploits the frozen CLIP backbone, refined through a knowledge-driven prompt tuning scheme that integrates high-level language priors with geometric cues from a lightweight 3D encoder. To adapt task-specific features effectively, we apply parameter-efficient fine-tuning to CLIP's encoders and design an entropy-guided view sampling strategy for selecting confident projections. Furthermore, an optimal transport-based alignment loss and an uncertainty-aware prototype alignment loss collaboratively bridge source-target distribution gaps while maintaining class separability. Extensive experiments on PointDA-10 and GraspNetPC-10 benchmarks show that CLIPoint3D achieves consistent 3-16% accuracy gains over both CLIP-based and conventional encoder-based baselines. Codes are available at https://github.com/SarthakM320/CLIPoint3D.

Pankhi Kashyap, Mainak Singha, Biplab Banerjee

Prompt learning (PL) has emerged as an effective strategy to adapt vision-language models (VLMs), such as CLIP, for downstream tasks under limited supervision. While PL has demonstrated strong generalization on natural image datasets, its transferability to remote sensing (RS) imagery remains underexplored. RS data present unique challenges, including multi-label scenes, high intra-class variability, and diverse spatial resolutions, that hinder the direct applicability of existing PL methods. In particular, current prompt-based approaches often struggle to identify dominant semantic cues and fail to generalize to novel classes in RS scenarios. To address these challenges, we propose BiMoRS, a lightweight bi-modal prompt learning framework tailored for RS tasks. BiMoRS employs a frozen image captioning model (e.g., BLIP-2) to extract textual semantic summaries from RS images. These captions are tokenized using a BERT tokenizer and fused with high-level visual features from the CLIP encoder. A lightweight cross-attention module then conditions a learnable query prompt on the fused textual-visual representation, yielding contextualized prompts without altering the CLIP backbone. We evaluate BiMoRS on four RS datasets across three domain generalization (DG) tasks and observe consistent performance gains, outperforming strong baselines by up to 2% on average. Codes are available at https://github.com/ipankhi/BiMoRS.

Jayesh Songara, Shivam Pande, Shabnam Choudhury et al.

In this research, we deal with the problem of visual question answering (VQA) in remote sensing. While remotely sensed images contain information significant for the task of identification and object detection, they pose a great challenge in their processing because of high dimensionality, volume and redundancy. Furthermore, processing image information jointly with language features adds additional constraints, such as mapping the corresponding image and language features. To handle this problem, we propose a cross attention based approach combined with information maximization. The CNN-LSTM based cross-attention highlights the information in the image and language modalities and establishes a connection between the two, while information maximization learns a low dimensional bottleneck layer, that has all the relevant information required to carry out the VQA task. We evaluate our method on two VQA remote sensing datasets of different resolutions. For the high resolution dataset, we achieve an overall accuracy of 79.11% and 73.87% for the two test sets while for the low resolution dataset, we achieve an overall accuracy of 85.98%.

Vaibhav Rathore, Divyam Gupta, Moloud Abdar et al.

We introduce the first unified framework for *Fine-Grained Domain-Generalized Generalized Category Discovery* (FG-DG-GCD), bringing open-world recognition closer to real-world deployment under domain shift. Unlike conventional GCD, which assumes labeled and unlabeled data come from the same distribution, DG-GCD learns only from labeled source data and must both recognize known classes and discover novel ones in unseen, unlabeled target domains. This problem is especially challenging in fine-grained settings, where subtle inter-class differences and large intra-class variation make domain generalization significantly harder. To support systematic evaluation, we establish the first *FG-DG-GCD benchmarks* by creating identity-preserving *painting* and *sketch* domains for CUB-200-2011, Stanford Cars, and FGVC-Aircraft using controlled diffusion-adapter stylization. On top of this ,we propose FoCUS, a single-stage framework that combines *Domain-Consistent Parts Discovery* (DCPD) for geometry-stable part reasoning with *Uncertainty-Aware Feature Augmentation* (UFA) for confidence-calibrated feature regularization through uncertainty-guided perturbations. Extensive experiments show that FoCUS outperforms strong GCD, FG-GCD, and DG-GCD baselines by **3.28%**, **9.68%**, and **2.07%**, respectively, in clustering accuracy on the proposed benchmarks. It also remains competitive on coarse-grained DG-GCD tasks while achieving nearly **3x** higher computational efficiency than the current state of the art. ^[Code and datasets will be released upon acceptance.]

Shivam Pande, Nassim Ait Ali Braham, Yi Wang et al.

Hyperspectral image (HSI) classification is gaining a lot of momentum in present time because of high inherent spectral information within the images. However, these images suffer from the problem of curse of dimensionality and usually require a large number samples for tasks such as classification, especially in supervised setting. Recently, to effectively train the deep learning models with minimal labelled samples, the unlabeled samples are also being leveraged in self-supervised and semi-supervised setting. In this work, we leverage the idea of semi-supervised learning to assist the discriminative self-supervised pretraining of the models. The proposed method takes different augmented views of the unlabeled samples as input and assigns them the same pseudo-label corresponding to the labelled sample from the downstream task. We train our model on two HSI datasets, namely Houston dataset (from data fusion contest, 2013) and Pavia university dataset, and show that the proposed approach performs better than self-supervised approach and supervised training.

Avigyan Bhattacharya, Mainak Singha, Ankit Jha et al.

We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-shot generalization performance, their effectiveness is limited when dealing with diverse domains during training and testing. Existing prompt learning techniques overlook the importance of incorporating domain and content information into the prompts, which results in a drop in performance while dealing with such multi-domain data. To address these challenges, we propose a solution that ensures domain-invariant prompt learning while enhancing the expressiveness of visual features. We observe that CLIP's vision encoder struggles to identify contextual image information, particularly when image patches are jumbled up. This issue is especially severe in optical remote sensing images, where land-cover classes exhibit well-defined contextual appearances. To this end, we introduce C-SAW, a method that complements CLIP with a self-supervised loss in the visual space and a novel prompt learning technique that emphasizes both visual domain and content-specific features. We keep the CLIP backbone frozen and introduce a small set of projectors for both the CLIP encoders to train C-SAW contrastively. Experimental results demonstrate the superiority of C-SAW across multiple remote sensing benchmarks and different generalization tasks.

Prathmesh Bele, Valay Bundele, Avigyan Bhattacharya et al.

Single-source open-domain generalization (SS-ODG) addresses the challenge of labeled source domains with supervision during training and unlabeled novel target domains during testing. The target domain includes both known classes from the source domain and samples from previously unseen classes. Existing techniques for SS-ODG primarily focus on calibrating source-domain classifiers to identify open samples in the target domain. However, these methods struggle with visually fine-grained open-closed data, often misclassifying open samples as closed-set classes. Moreover, relying solely on a single source domain restricts the model's ability to generalize. To overcome these limitations, we propose a novel framework called SODG-Net that simultaneously synthesizes novel domains and generates pseudo-open samples using a learning-based objective, in contrast to the ad-hoc mixing strategies commonly found in the literature. Our approach enhances generalization by diversifying the styles of known class samples using a novel metric criterion and generates diverse pseudo-open samples to train a unified and confident multi-class classifier capable of handling both open and closed-set data. Extensive experimental evaluations conducted on multiple benchmarks consistently demonstrate the superior performance of SODG-Net compared to the literature.

Debabrata Pal, Deeptej More, Sai Bhargav et al.

Few-shot learning has made impressive strides in addressing the crucial challenges of recognizing unknown samples from novel classes in target query sets and managing visual shifts between domains. However, existing techniques fall short when it comes to identifying target outliers under domain shifts by learning to reject pseudo-outliers from the source domain, resulting in an incomplete solution to both problems. To address these challenges comprehensively, we propose a novel approach called Domain Adaptive Few-Shot Open Set Recognition (DA-FSOS) and introduce a meta-learning-based architecture named DAFOSNET. During training, our model learns a shared and discriminative embedding space while creating a pseudo open-space decision boundary, given a fully-supervised source domain and a label-disjoint few-shot target domain. To enhance data density, we use a pair of conditional adversarial networks with tunable noise variances to augment both domains closed and pseudo-open spaces. Furthermore, we propose a domain-specific batch-normalized class prototypes alignment strategy to align both domains globally while ensuring class-discriminativeness through novel metric objectives. Our training approach ensures that DAFOS-NET can generalize well to new scenarios in the target domain. We present three benchmarks for DA-FSOS based on the Office-Home, mini-ImageNet/CUB, and DomainNet datasets and demonstrate the efficacy of DAFOS-NET through extensive experimentation

Mainak Singha, Ankit Jha, Shirsha Bose et al.

We delve into Open Domain Generalization (ODG), marked by domain and category shifts between training's labeled source and testing's unlabeled target domains. Existing solutions to ODG face limitations due to constrained generalizations of traditional CNN backbones and errors in detecting target open samples in the absence of prior knowledge. Addressing these pitfalls, we introduce ODG-CLIP, harnessing the semantic prowess of the vision-language model, CLIP. Our framework brings forth three primary innovations: Firstly, distinct from prevailing paradigms, we conceptualize ODG as a multi-class classification challenge encompassing both known and novel categories. Central to our approach is modeling a unique prompt tailored for detecting unknown class samples, and to train this, we employ a readily accessible stable diffusion model, elegantly generating proxy images for the open class. Secondly, aiming for domain-tailored classification (prompt) weights while ensuring a balance of precision and simplicity, we devise a novel visual stylecentric prompt learning mechanism. Finally, we infuse images with class-discriminative knowledge derived from the prompt space to augment the fidelity of CLIP's visual embeddings. We introduce a novel objective to safeguard the continuity of this infused semantic intel across domains, especially for the shared classes. Through rigorous testing on diverse datasets, covering closed and open-set DG contexts, ODG-CLIP demonstrates clear supremacy, consistently outpacing peers with performance boosts between 8%-16%. Code will be available at https://github.com/mainaksingha01/ODG-CLIP.

Mainak Singha, Ankit Jha, Divyam Gupta et al.

We address the challenges inherent in sketch-based image retrieval (SBIR) across various settings, including zero-shot SBIR, generalized zero-shot SBIR, and fine-grained zero-shot SBIR, by leveraging the vision-language foundation model CLIP. While recent endeavors have employed CLIP to enhance SBIR, these approaches predominantly follow uni-modal prompt processing and overlook to exploit CLIP's integrated visual and textual capabilities fully. To bridge this gap, we introduce SpLIP, a novel multi-modal prompt learning scheme designed to operate effectively with frozen CLIP backbones. We diverge from existing multi-modal prompting methods that treat visual and textual prompts independently or integrate them in a limited fashion, leading to suboptimal generalization. SpLIP implements a bi-directional prompt-sharing strategy that enables mutual knowledge exchange between CLIP's visual and textual encoders, fostering a more cohesive and synergistic prompt processing mechanism that significantly reduces the semantic gap between the sketch and photo embeddings. In addition to pioneering multi-modal prompt learning, we propose two innovative strategies for further refining the embedding space. The first is an adaptive margin generation for the sketch-photo triplet loss, regulated by CLIP's class textual embeddings. The second introduces a novel task, termed conditional cross-modal jigsaw, aimed at enhancing fine-grained sketch-photo alignment by implicitly modeling sketches' viable patch arrangement using knowledge of unshuffled photos. Our comprehensive experimental evaluations across multiple benchmarks demonstrate the superior performance of SpLIP in all three SBIR scenarios. Project page: https://mainaksingha01.github.io/SpLIP/ .

Sandika Biswas, Qianyi Wu, Biplab Banerjee et al.

Despite advancements in Neural Implicit models for 3D surface reconstruction, handling dynamic environments with interactions between arbitrary rigid, non-rigid, or deformable entities remains challenging. The generic reconstruction methods adaptable to such dynamic scenes often require additional inputs like depth or optical flow or rely on pre-trained image features for reasonable outcomes. These methods typically use latent codes to capture frame-by-frame deformations. Another set of dynamic scene reconstruction methods, are entity-specific, mostly focusing on humans, and relies on template models. In contrast, some template-free methods bypass these requirements and adopt traditional LBS (Linear Blend Skinning) weights for a detailed representation of deformable object motions, although they involve complex optimizations leading to lengthy training times. To this end, as a remedy, this paper introduces TFS-NeRF, a template-free 3D semantic NeRF for dynamic scenes captured from sparse or single-view RGB videos, featuring interactions among two entities and more time-efficient than other LBS-based approaches. Our framework uses an Invertible Neural Network (INN) for LBS prediction, simplifying the training process. By disentangling the motions of interacting entities and optimizing per-entity skinning weights, our method efficiently generates accurate, semantically separable geometries. Extensive experiments demonstrate that our approach produces high-quality reconstructions of both deformable and non-deformable objects in complex interactions, with improved training efficiency compared to existing methods.

Saikat Dutta, Biplab Banerjee, Hamid Rezatofighi

Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inference. Although modern vision-language models (VLMs) support strong open-vocabulary recognition, their representations learned through global contrastive objectives remain suboptimal for dense prediction, prompting many OVSS methods to depend on limited adaptation or refinement of image-text similarity maps. This, in turn, restricts spatial precision and robustness in complex, cluttered scenes. We introduce dinov3.seg, extending dinov3.txt into a dedicated framework for OVSS. Our contributions are four-fold. First, we design a task-specific architecture tailored to this backbone, systematically adapting established design principles from prior open-vocabulary segmentation work. Second, we jointly leverage text embeddings aligned with both the global [CLS] token and local patch-level visual features from ViT-based encoder, effectively combining semantic discrimination with fine-grained spatial locality. Third, unlike prior approaches that rely primarily on post hoc similarity refinement, we perform early refinement of visual representations prior to image-text interaction, followed by late refinement of the resulting image-text correlation features, enabling more accurate and robust dense predictions in cluttered scenes. Finally, we propose a high-resolution local-global inference strategy based on sliding-window aggregation, which preserves spatial detail while maintaining global context. We conduct extensive experiments on five widely adopted OVSS benchmarks to evaluate our approach. The results demonstrate its effectiveness and robustness, consistently outperforming current state-of-the-art methods.

Maram Hasan, Md Aminur Hossain, Savitra Roy et al.

Effective foundation modeling in remote sensing requires spatially aligned heterogeneous modalities coupled with semantically grounded supervision, yet such resources remain limited at scale. We present GeoMeld, a large-scale multimodal dataset with approximately 2.5 million spatially aligned samples. The dataset spans diverse modalities and resolutions and is constructed under a unified alignment protocol for modality-aware representation learning. GeoMeld provides semantically grounded language supervision through an agentic captioning framework that synthesizes and verifies annotations from spectral signals, terrain statistics, and structured geographic metadata, encoding measurable cross-modality relationships within textual descriptions. To leverage this dataset, we introduce GeoMeld-FM, a pretraining framework that combines multi-pretext masked autoencoding over aligned modalities, JEPA representation learning, and caption-vision contrastive alignment. This joint objective enables the learned representation space to capture both reliable cross-sensor physical consistency and grounded semantics. Experiments demonstrate consistent gains in downstream transfer and cross-sensor robustness. Together, GeoMeld and GeoMeld-FM establish a scalable reference framework for semantically grounded multi-modal foundation modeling in remote sensing.

Sayan Rakshit, Hmrishav Bandyopadhyay, Nibaran Das et al.

Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains when training with new domains. We illuminate this current neural network model weakness and develop a forgetting-resistant incremental learning strategy. Here, we propose a new unsupervised incremental open-set domain adaptation (IOSDA) issue for image classification. Open-set domain adaptation adds complexity to the incremental domain adaptation issue since each target domain has more classes than the Source domain. In IOSDA, the model learns training with domain streams phase by phase in incremented time. Inference uses test data from all target domains without revealing their identities. We proposed IOSDA-Net, a two-stage learning pipeline, to solve the problem. The first module replicates prior domains from random noise using a generative framework and creates a pseudo source domain. In the second step, this pseudo source is adapted to the present target domain. We test our model on Office-Home, DomainNet, and UPRN-RSDA, a newly curated optical remote sensing dataset.

Avik Bhattacharya, Siddhant Dnyanesh Gole, Subhasis Chaudhuri et al.

Activation functions are central to deep networks, influencing non-linearity, feature learning, convergence, and robustness. This paper proposes the Adaptive Arctangent Gated Activation (ArcGate) function, a flexible formulation that generates a broad spectrum of activation shapes via a three-stage non-linear transformation. Unlike conventional fixed-shape activations such as ReLU, GELU, or SiLU, ArcGate uses seven learnable parameters per layer, allowing the neural network to autonomously optimize its non-linearity to the specific requirements of the feature hierarchy and data distribution. We evaluate ArcGate using ResNet-50 and Vision Transformer (ViT-B/16) architectures on three widely used remote sensing benchmarks: PatternNet, UC Merced Land Use, and the 13-band EuroSAT MSI multispectral dataset. Experimental results show that ArcGate consistently outperforms standard baselines, achieving a peak overall accuracy of 99.67% on PatternNet. Most notably, ArcGate exhibits superior structural resilience in noisy environments, maintaining a 26.65% performance lead over ReLU under moderate Gaussian noise (standard deviation 0.1). Analysis of the learned parameters reveals a depth-dependent functional evolution, where the model increases gating strength in deeper layers to enhance signal propagation. These findings suggest that ArcGate is a robust and adaptive general node activation function for high-resolution earth observation tasks.

Yuzhen Hu, Biplab Banerjee, Saurabh Prasad

Hyperspectral imaging (HSI) enables detailed land cover classification, yet low spatial resolution and sparse annotations pose significant challenges. We present a label-efficient framework that leverages spatial features from a frozen diffusion model pretrained on natural images. Our approach extracts low-level representations from high-resolution decoder layers at early denoising timesteps, which transfer effectively to the low-texture structure of HSI. To integrate spectral and spatial information, we introduce a lightweight FiLM-based fusion module that adaptively modulates frozen spatial features using spectral cues, enabling robust multimodal learning under sparse supervision. Experiments on two recent hyperspectral datasets demonstrate that our method outperforms state-of-the-art approaches using only the provided sparse training labels. Ablation studies further highlight the benefits of diffusion-derived features and spectral-aware fusion. Overall, our results indicate that pretrained diffusion models can support domain-agnostic, label-efficient representation learning for remote sensing and broader scientific imaging tasks.

Md Aminur Hossain, Parekh Valkesh, Ayush V. Patel et al.

Remote Sensing (RS) single-image super-resolution aims to reconstruct high-resolution imagery from low-resolution observations while preserving fine spatial structures. Recent Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling throughshifted-window self-attention, but their feed-forward networks remain generic channel-mixing modules and do not separate low-frequency structural content from high-frequency residual detail. To address this limitation, we propose SFG-SwinSR, a Spatial-Frequency Gated Swin Transformer for single-image super-resolution in remote sensing. SFG-SwinSR modifies the original Swin2SR attention block by replacing each transformer block's standard feed-forward network with a lightweight Spatial-Frequency Gated Feed-Forward Network (SFG-FFN). The module estimates low-frequency content via a depthwise-blur branch, extracts high-frequency residuals by subtraction, refines them with a lightweight spatial branch, and adaptively injects detail through a bottleneck gate. Experiments on SpaceNet and SEN2VENμS show that SFG-SwinSR improves reconstruction quality under the evaluated settings. On SpaceNet, it achieves 45.19 dB PSNR and 0.9852 SSIM, indicating effective enhancement of high-frequency details. This demonstrates that spatial-frequency transformation within the transformer feed-forward network improves detail reconstruction in RS super-resolution.

Mainak Singha, Subhankar Roy, Sarthak Mehrotra et al.

In federated learning, textual prompt tuning adapts Vision-Language Models (e.g., CLIP) by tuning lightweight input tokens (or prompts) on local client data, while keeping network weights frozen. After training, only the prompts are shared by the clients with the central server for aggregation. However, textual prompt tuning suffers from overfitting to known concepts, limiting its generalizability to unseen concepts. To address this limitation, we propose Multimodal Visual Prompt Tuning (FedMVP) that conditions the prompts on multimodal contextual information - derived from the input image and textual attribute features of a class. At the core of FedMVP is a PromptFormer module that synergistically aligns textual and visual features through a cross-attention mechanism. The dynamically generated multimodal visual prompts are then input to the frozen vision encoder of CLIP, and trained with a combination of CLIP similarity loss and a consistency loss. Extensive evaluation on 20 datasets, spanning three generalization settings, demonstrates that FedMVP not only preserves performance on in-distribution classes and domains, but also displays higher generalizability to unseen classes and domains, surpassing state-of-the-art methods by a notable margin of +1.57% - 2.26%. Code is available at https://github.com/mainaksingha01/FedMVP.

Hariseetharam Gunduboina, Muhammad Haris Khan, Biplab Banerjee

In recent years, large-scale vision-language models (VLMs) like CLIP have gained attention for their zero-shot inference using instructional text prompts. While these models excel in general computer vision, their potential for domain generalization in remote sensing (RS) remains underexplored. Existing approaches enhance prompt learning by generating visual prompt tokens but rely on full-image features, introducing noise and background artifacts that vary within a class, causing misclassification. To address this, we propose FrogDogNet, a novel prompt learning framework integrating Fourier frequency filtering and self-attention to improve RS scene classification and domain generalization. FrogDogNet selectively retains invariant low-frequency components while eliminating noise and irrelevant backgrounds, ensuring robust feature representation across domains. The model first extracts significant features via projection and self-attention, then applies frequency-based filtering to preserve essential structural information for prompt learning. Extensive experiments on four RS datasets and three domain generalization tasks show that FrogDogNet consistently outperforms state-of-the-art prompt learning methods, demonstrating superior adaptability across domain shifts. Our findings highlight the effectiveness of frequency-based invariant feature retention in generalization, paving the way for broader applications. Our code is available at https://github.com/HariseetharamG/FrogDogNet

Md Aminur Hossain, Ayush V. Patel, Siddhant Gole et al.

Remote sensing semantic segmentation requires models that can jointly capture fine spatial details and high-level semantic context across complex scenes. While classical encoder-decoder architectures such as U-Net remain strong baselines, they often struggle to fully exploit global semantics and structured feature interactions. In this work, we propose HQF-Net, a hybrid quantum-classical multi-scale fusion network for remote sensing image segmentation. HQF-Net integrates multi-scale semantic guidance from a frozen DINOv3 ViT-L/16 backbone with a customized U-Net architecture through a Deformable Multiscale Cross-Attention Fusion (DMCAF) module. To enhance feature refinement, the framework further introduces quantum-enhanced skip connections (QSkip) and a Quantum bottleneck with Mixture-of-Experts (QMoE), which combines complementary local, global, and directional quantum circuits within an adaptive routing mechanism. Experiments on three remote sensing benchmarks show consistent improvements with the proposed design. HQF-Net achieves 0.8568 mIoU and 96.87% overall accuracy on LandCover.ai, 71.82% mIoU on OpenEarthMap, and 55.28% mIoU with 99.37% overall accuracy on SeasoNet. An architectural ablation study further confirms the contribution of each major component. These results show that structured hybrid quantum-classical feature processing is a promising direction for improving remote sensing semantic segmentation under near-term quantum constraints.

Md Aminur Hossain, Ayush V. Patel, Biplab Banerjee

Hybrid quantum-classical models offer a promising route for learning from complex data; however, their application to multi-band remote sensing imagery often relies on generic, data-agnostic quantum circuits that fail to account for channel-specific statistical variability. In this work, we propose a data-driven framework that maps band-level statistics such as Shannon Entropy, Variance, Spectral Flatness, and Edge Density to the hyperparameters of customized quantum circuits. Building on this framework, we introduce QMC-Net, a hybrid architecture that processes six data channels using band-specific quantum circuits, enabling adaptive quantum feature encoding and transformation across channels. Experiments on the EuroSAT and SAT-6 datasets demonstrate that QMC-Net achieves accuracies of 93.80 % and 99.34 %, respectively, while a residual-enhanced variant further improves performance to 94.69 % and 99.39 %. These results consistently outperform strong classical baselines and monolithic hybrid quantum models, highlighting the effectiveness of data-aware quantum circuit design under NISQ constraints.

Md Aminur Hossain, Ayush V. Patel, Ikshwaku Vanani et al.

Semantic segmentation in remote sensing is commonly addressed using classical deep learning architectures such as U-Net, which require a large number of parameters to model complex spatial relationships. Quantum machine learning (QML) provides an alternative representation paradigm by mapping classical features into quantum states, but its direct application to high-dimensional images remains challenging under near-term quantum hardware constraints. In this work, we propose HQ-UNet, a hybrid quantum-classical U-Net architecture that integrates a compact parameterized quantum circuit at the bottleneck of a classical U-Net. The proposed design uses a non-pooling quantum convolutional module to enrich highly compressed encoder features before decoding, while keeping the quantum component shallow and parameter-efficient. Experiments on the LandCover.ai dataset show that HQ-UNet achieves a mean IoU of 0.8050 and an overall accuracy of 94.76%, outperforming the classical U-Net baseline. These results suggest that compact quantum bottlenecks can enhance feature representation for remote sensing image segmentation under near-term quantum constraints. This highlights the potential of hybrid quantum-classical designs as a promising direction for parameter-efficient dense prediction in Earth observation.

Sai Bhargav Rongali, Sarthak Mehrotra, Ankit Jha et al.

In Generalized Category Discovery (GCD), we cluster unlabeled samples of known and novel classes, leveraging a training dataset of known classes. A salient challenge arises due to domain shifts between these datasets. To address this, we present a novel setting: Across Domain Generalized Category Discovery (AD-GCD) and bring forth CDAD-NET (Class Discoverer Across Domains) as a remedy. CDAD-NET is architected to synchronize potential known class samples across both the labeled (source) and unlabeled (target) datasets, while emphasizing the distinct categorization of the target data. To facilitate this, we propose an entropy-driven adversarial learning strategy that accounts for the distance distributions of target samples relative to source-domain class prototypes. Parallelly, the discriminative nature of the shared space is upheld through a fusion of three metric learning objectives. In the source domain, our focus is on refining the proximity between samples and their affiliated class prototypes, while in the target domain, we integrate a neighborhood-centric contrastive learning mechanism, enriched with an adept neighborsmining approach. To further accentuate the nuanced feature interrelation among semantically aligned images, we champion the concept of conditional image inpainting, underscoring the premise that semantically analogous images prove more efficacious to the task than their disjointed counterparts. Experimentally, CDAD-NET eclipses existing literature with a performance increment of 8-15% on three AD-GCD benchmarks we present.

Izzeddin Teeti, Aniket Thomas, Munish Monga et al.

We present ASTRA (A} Scene-aware TRAnsformer-based model for trajectory prediction), a light-weight pedestrian trajectory forecasting model that integrates the scene context, spatial dynamics, social inter-agent interactions and temporal progressions for precise forecasting. We utilised a U-Net-based feature extractor, via its latent vector representation, to capture scene representations and a graph-aware transformer encoder for capturing social interactions. These components are integrated to learn an agent-scene aware embedding, enabling the model to learn spatial dynamics and forecast the future trajectory of pedestrians. The model is designed to produce both deterministic and stochastic outcomes, with the stochastic predictions being generated by incorporating a Conditional Variational Auto-Encoder (CVAE). ASTRA also proposes a simple yet effective weighted penalty loss function, which helps to yield predictions that outperform a wide array of state-of-the-art deterministic and generative models. ASTRA demonstrates an average improvement of 27%/10% in deterministic/stochastic settings on the ETH-UCY dataset, and 26% improvement on the PIE dataset, respectively, along with seven times fewer parameters than the existing state-of-the-art model (see Figure 1). Additionally, the model's versatility allows it to generalize across different perspectives, such as Bird's Eye View (BEV) and Ego-Vehicle View (EVV).

Mohamad Hassan N C, Divyam Gupta, Mainak Singha et al.

We introduce Low-Shot Open-Set Domain Generalization (LSOSDG), a novel paradigm unifying low-shot learning with open-set domain generalization (ODG). While prompt-based methods using models like CLIP have advanced DG, they falter in low-data regimes (e.g., 1-shot) and lack precision in detecting open-set samples with fine-grained semantics related to training classes. To address these challenges, we propose OSLOPROMPT, an advanced prompt-learning framework for CLIP with two core innovations. First, to manage limited supervision across source domains and improve DG, we introduce a domain-agnostic prompt-learning mechanism that integrates adaptable domain-specific cues and visually guided semantic attributes through a novel cross-attention module, besides being supported by learnable domain- and class-generic visual prompts to enhance cross-modal adaptability. Second, to improve outlier rejection during inference, we classify unfamiliar samples as "unknown" and train specialized prompts with systematically synthesized pseudo-open samples that maintain fine-grained relationships to known classes, generated through a targeted query strategy with off-the-shelf foundation models. This strategy enhances feature learning, enabling our model to detect open samples with varied granularity more effectively. Extensive evaluations across five benchmarks demonstrate that OSLOPROMPT establishes a new state-of-the-art in LSOSDG, significantly outperforming existing methods.

Aryan Bhosale, Samrat Mukherjee, Biplab Banerjee et al.

This paper explores the utility of diffusion-based models for anomaly detection, focusing on their efficacy in identifying deviations in both compact and high-resolution datasets. Diffusion-based architectures, including Denoising Diffusion Probabilistic Models (DDPMs) and Diffusion Transformers (DiTs), are evaluated for their performance using reconstruction objectives. By leveraging the strengths of these models, this study benchmarks their performance against traditional anomaly detection methods such as Isolation Forests, One-Class SVMs, and COPOD. The results demonstrate the superior adaptability, scalability, and robustness of diffusion-based methods in handling complex real-world anomaly detection tasks. Key findings highlight the role of reconstruction error in enhancing detection accuracy and underscore the scalability of these models to high-dimensional datasets. Future directions include optimizing encoder-decoder architectures and exploring multi-modal datasets to further advance diffusion-based anomaly detection.

Saikat Dutta, Akhil Vasim, Siddhant Gole et al.

Image segmentation beyond predefined categories is a key challenge in remote sensing, where novel and unseen classes often emerge during inference. Open-vocabulary image Segmentation addresses these generalization issues in traditional supervised segmentation models while reducing reliance on extensive per-pixel annotations, which are both expensive and labor-intensive to obtain. Most Open-Vocabulary Segmentation (OVS) methods are designed for natural images but struggle with remote sensing data due to scale variations, orientation changes, and complex scene compositions. This necessitates the development of OVS approaches specifically tailored for remote sensing. In this context, we propose AerOSeg, a novel OVS approach for remote sensing data. First, we compute robust image-text correlation features using multiple rotated versions of the input image and domain-specific prompts. These features are then refined through spatial and class refinement blocks. Inspired by the success of the Segment Anything Model (SAM) in diverse domains, we leverage SAM features to guide the spatial refinement of correlation features. Additionally, we introduce a semantic back-projection module and loss to ensure the seamless propagation of SAM's semantic information throughout the segmentation pipeline. Finally, we enhance the refined correlation features using a multi-scale attention-aware decoder to produce the final segmentation map. We validate our SAM-guided Open-Vocabulary Remote Sensing Segmentation model on three benchmark remote sensing datasets: iSAID, DLRSD, and OpenEarthMap. Our model outperforms state-of-the-art open-vocabulary segmentation methods, achieving an average improvement of 2.54 h-mIoU.

Shabnam Choudhury, Yash Salunkhe, Sarthak Mehrotra et al.

The rapid expansion of remote sensing image archives demands the development of strong and efficient techniques for content-based image retrieval (RS-CBIR). This paper presents REJEPA (Retrieval with Joint-Embedding Predictive Architecture), an innovative self-supervised framework designed for unimodal RS-CBIR. REJEPA utilises spatially distributed context token encoding to forecast abstract representations of target tokens, effectively capturing high-level semantic features and eliminating unnecessary pixel-level details. In contrast to generative methods that focus on pixel reconstruction or contrastive techniques that depend on negative pairs, REJEPA functions within feature space, achieving a reduction in computational complexity of 40-60% when compared to pixel-reconstruction baselines like Masked Autoencoders (MAE). To guarantee strong and varied representations, REJEPA incorporates Variance-Invariance-Covariance Regularisation (VICReg), which prevents encoder collapse by promoting feature diversity and reducing redundancy. The method demonstrates an estimated enhancement in retrieval accuracy of 5.1% on BEN-14K (S1), 7.4% on BEN-14K (S2), 6.0% on FMoW-RGB, and 10.1% on FMoW-Sentinel compared to prominent SSL techniques, including CSMAE-SESD, Mask-VLM, SatMAE, ScaleMAE, and SatMAE++, on extensive RS benchmarks BEN-14K (multispectral and SAR data), FMoW-RGB and FMoW-Sentinel. Through effective generalisation across sensor modalities, REJEPA establishes itself as a sensor-agnostic benchmark for efficient, scalable, and precise RS-CBIR, addressing challenges like varying resolutions, high object density, and complex backgrounds with computational efficiency.

Bhupendra Solanki, Ashwin Nair, Mainak Singha et al.

Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes. To address the challenge of transferring features from known to unknown classes while mitigating model bias, we introduce GraphVL, a novel approach for vision-language modeling in GCD, leveraging CLIP. Our method integrates a graph convolutional network (GCN) with CLIP's text encoder to preserve class neighborhood structure. We also employ a lightweight visual projector for image data, ensuring discriminative features through margin-based contrastive losses for image-text mapping. This neighborhood preservation criterion effectively regulates the semantic space, making it less sensitive to known classes. Additionally, we learn textual prompts from known classes and align them to create a more contextually meaningful semantic feature space for the GCN layer using a contextual similarity loss. Finally, we represent unlabeled samples based on their semantic distance to class prompts from the GCN, enabling semi-supervised clustering for class discovery and minimizing errors. Our experiments on seven benchmark datasets consistently demonstrate the superiority of GraphVL when integrated with the CLIP backbone.

Vaibhav Rathore, Shubhranil B, Saikat Dutta et al.

Generalized Class Discovery (GCD) clusters base and novel classes in a target domain using supervision from a source domain with only base classes. Current methods often falter with distribution shifts and typically require access to target data during training, which can sometimes be impractical. To address this issue, we introduce the novel paradigm of Domain Generalization in GCD (DG-GCD), where only source data is available for training, while the target domain, with a distinct data distribution, remains unseen until inference. To this end, our solution, DG2CD-Net, aims to construct a domain-independent, discriminative embedding space for GCD. The core innovation is an episodic training strategy that enhances cross-domain generalization by adapting a base model on tasks derived from source and synthetic domains generated by a foundation model. Each episode focuses on a cross-domain GCD task, diversifying task setups over episodes and combining open-set domain adaptation with a novel margin loss and representation learning for optimizing the feature space progressively. To capture the effects of fine-tuning on the base model, we extend task arithmetic by adaptively weighting the local task vectors concerning the fine-tuned models based on their GCD performance on a validation distribution. This episodic update mechanism boosts the adaptability of the base model to unseen targets. Experiments across three datasets confirm that DG2CD-Net outperforms existing GCD methods customized for DG-GCD.

Dipesh Tamboli, Souradip Chakraborty, Aditya Malusare et al.

Text-to-image (T2I) diffusion models have made remarkable advancements, yet aligning them with diverse preferences remains a persistent challenge. Current methods often optimize single metrics or depend on narrowly curated datasets, leading to overfitting and limited generalization across key visual quality metrics. We present BalancedDPO, a novel extension of Direct Preference Optimization (DPO) that addresses these limitations by simultaneously aligning T2I diffusion models with multiple metrics, including human preference, CLIP score, and aesthetic quality. Our key novelty lies in aggregating consensus labels from diverse metrics in the preference distribution space as compared to existing reward mixing approaches, enabling robust and scalable multi-metric alignment while maintaining the simplicity of the standard DPO pipeline that we refer to as BalancedDPO. Our evaluations on the Pick-a-Pic, PartiPrompt and HPD datasets show that BalancedDPO achieves state-of-the-art results, outperforming existing approaches across all major metrics. BalancedDPO improves the average win rates by 15%, 7.1%, and 10.3% on Pick-a-pic, PartiPrompt and HPD, respectively, from the DiffusionDPO.

Sanchar Palit, Biplab Banerjee, Subhasis Chaudhuri

We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each step to retain knowledge poses challenges. This is compounded by the crucial need to mitigate catastrophic forgetting, particularly given the limited access to past datasets, which complicates maintaining correspondence between network parameters and datasets across all sessions. Current methods using Variational Inference with KL divergence risk catastrophic forgetting during uncertain node updates and coupled disruptions in certain nodes. To address these challenges, we propose the following strategies. To reduce the storage of the dense layer parameters, we propose a parameter distribution learning method that significantly reduces the storage requirements. In the continual learning framework employing variational inference, our study introduces a regularization term that specifically targets the dynamics and population of the mean and variance of the parameters. This term aims to retain the benefits of KL divergence while addressing related challenges. To ensure proper correspondence between network parameters and the data, our method introduces an importance-weighted Evidence Lower Bound term to capture data and parameter correlations. This enables storage of common and distinctive parameter hyperspace bases. The proposed method partitions the parameter space into common and distinctive subspaces, with conditions for effective backward and forward knowledge transfer, elucidating the network-parameter dataset correspondence. The experimental results demonstrate the effectiveness of our method across diverse datasets and various combinations of sequential datasets, yielding superior performance compared to existing approaches.

Valay Bundele, Mahesh Bhupati, Biplab Banerjee et al.

The study of vision-and-language navigation (VLN) has typically relied on expert trajectories, which may not always be available in real-world situations due to the significant effort required to collect them. On the other hand, existing approaches to training VLN agents that go beyond available expert data involve data augmentations or online exploration which can be tedious and risky. In contrast, it is easy to access large repositories of suboptimal offline trajectories. Inspired by research in offline reinforcement learning (ORL), we introduce a new problem setup of VLN-ORL which studies VLN using suboptimal demonstration data. We introduce a simple and effective reward-conditioned approach that can account for dataset suboptimality for training VLN agents, as well as benchmarks to evaluate progress and promote research in this area. We empirically study various noise models for characterizing dataset suboptimality among other unique challenges in VLN-ORL and instantiate it for the VLN$\circlearrowright$BERT and MTVM architectures in the R2R and RxR environments. Our experiments demonstrate that the proposed reward-conditioned approach leads to significant performance improvements, even in complex and intricate environments.

Vaibhav Rathore, Divyam Gupta, Biplab Banerjee

Generalized Category Discovery (GCD) aims to classify test-time samples into either seen categories** -- available during training -- or novel ones, without relying on label supervision. Most existing GCD methods assume simultaneous access to labeled and unlabeled data during training and arising from the same domain, limiting applicability in open-world scenarios involving distribution shifts. Domain Generalization with GCD (DG-GCD) lifts this constraint by requiring models to generalize to unseen domains containing novel categories, without accessing targetdomain data during training. The only prior DG-GCD method, DG2CD-Net, relies on episodic training with multiple synthetic domains and task vector aggregation, incurring high computational cost and error accumulation. We propose HIDISC, a hyperbolic representation learning framework that achieves domain and category-level generalization without episodic simulation. To expose the model to minimal but diverse domain variations, we augment the source domain using GPT-guided diffusion, avoiding overfitting while maintaining efficiency. To structure the representation space, we introduce Tangent CutMix, a curvature-aware interpolation that synthesizes pseudo-novel samples in tangent space, preserving manifold consistency. A unified loss -- combining penalized Busemann alignment, hybrid hyperbolic contrastive regularization, and adaptive outlier repulsion -- **facilitates compact, semantically structured embeddings. A learnable curvature parameter further adapts the geometry to dataset complexity. HIDISC achieves state-of-the-art results on PACS , Office-Home , and DomainNet, consistently outperforming the existing Euclidean and hyperbolic (DG)-GCD baselines.