Oindrila Saha

Oindrila Saha, Zezhou Cheng, Subhransu Maji

A significant bottleneck in training deep networks for part segmentation is the cost of obtaining detailed annotations. We propose a framework to exploit coarse labels such as figure-ground masks and keypoint locations that are readily available for some categories to improve part segmentation models. A key challenge is that these annotations were collected for different tasks and with different labeling styles and cannot be readily mapped to the part labels. To this end, we propose to jointly learn the dependencies between labeling styles and the part segmentation model, allowing us to utilize supervision from diverse labels. To evaluate our approach we develop a benchmark on the Caltech-UCSD birds and OID Aircraft dataset. Our approach outperforms baselines based on multi-task learning, semi-supervised learning, and competitive methods relying on loss functions manually designed to exploit sparse-supervision.

Oindrila Saha, Subhransu Maji

We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as effective, and posit that recognizing part-specific variations is crucial for fine-grained categorization. We present an iterative learning approach that incorporates part-centric equivariance and invariance objectives. First, pixel representations are clustered to discover parts. We analyze the representations from convolutional and vision transformer networks that are best suited for this task. Then, a part-centric learning step aggregates and contrasts representations of parts within an image. We show that this improves the performance on image classification and part segmentation tasks across datasets. For example, under a linear-evaluation scheme, the classification accuracy of a ResNet50 trained on ImageNet using DetCon, a self-supervised learning approach, improves from 35.4% to 42.0% on the Caltech-UCSD Birds, from 35.5% to 44.1% on the FGVC Aircraft, and from 29.7% to 37.4% on the Stanford Cars. We also observe significant gains in few-shot part segmentation tasks using the proposed technique, while instance-discriminative learning was not as effective. Smaller, yet consistent, improvements are also observed for stronger networks based on transformers.

Logan Lawrence, Mustafa Chasmai, Rangel Daroya et al.

Fine-grained bird species identification in the wild is frequently unanswerable from a single image: key cues may be non-visual (e.g. vocalization), or obscured due to occlusion, camera angle, or low resolution. Yet today's multimodal systems are typically judged on answerable, in-schema cases, encouraging confident guesses rather than principled abstention. We propose the RealBirdID benchmark: given an image of a bird, a system should either answer with a species or abstain with a concrete, evidence-based rationale: "requires vocalization," "low quality image," or "view obstructed". For each genus, the dataset includes a validation split composed of curated unanswerable examples with labeled rationales, paired with a companion set of clearly answerable instances. We find that (1) the species identification on the answerable set is challenging for a variety of open-source and proprietary models (less than 13% accuracy for MLLMs including GPT-5 and Gemini-2.5 Pro), (2) models with greater classification ability are not necessarily more calibrated to abstain from unanswerable examples, and (3) that MLLMs generally fail at providing correct reasons even when they do abstain. RealBirdID establishes a focused target for abstention-aware fine-grained recognition and a recipe for measuring progress.

Oindrila Saha, Vojtech Krs, Radomir Mech et al.

Recent progress in large language models (LLMs) has shown that reasoning improves when intermediate thoughts are externalized into explicit workspaces, such as chain-of-thought traces or tool-augmented reasoning. Yet, visual language models (VLMs) lack an analogous mechanism for spatial reasoning, limiting their ability to generate images that accurately reflect geometric relations, object identities, and compositional intent. We introduce the concept of a spatial scratchpad -- a 3D reasoning substrate that bridges linguistic intent and image synthesis. Given a text prompt, our framework parses subjects and background elements, instantiates them as editable 3D meshes, and employs agentic scene planning for placement, orientation, and viewpoint selection. The resulting 3D arrangement is rendered back into the image domain with identity-preserving cues, enabling the VLM to generate spatially consistent and visually coherent outputs. Unlike prior 2D layout-based methods, our approach supports intuitive 3D edits that propagate reliably into final images. Empirically, it achieves a 32% improvement in text alignment on GenAI-Bench, demonstrating the benefit of explicit 3D reasoning for precise, controllable image generation. Our results highlight a new paradigm for vision-language models that deliberate not only in language, but also in space. Code and visualizations at https://oindrilasaha.github.io/3DScratchpad/

Oindrila Saha, Grant Van Horn, Subhransu Maji

The zero-shot performance of existing vision-language models (VLMs) such as CLIP is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources of information -- descriptions of categories generated by large language models (LLMs) and abundant, fine-grained image classification datasets -- to improve the zero-shot classification performance of VLMs across fine-grained domains. On the technical side, we develop methods to train VLMs with this "bag-level" image-text supervision. We find that simply using these attributes at test-time does not improve performance, but our training strategy, for example, on the iNaturalist dataset, leads to an average improvement of 4-5% in zero-shot classification accuracy for novel categories of birds and flowers. Similar improvements are observed in domains where a subset of the categories was used to fine-tune the model. By prompting LLMs in various ways, we generate descriptions that capture visual appearance, habitat, and geographic regions and pair them with existing attributes such as the taxonomic structure of the categories. We systematically evaluate their ability to improve zero-shot categorization in natural domains. Our findings suggest that geographic priors can be just as effective and are complementary to visual appearance. Our method also outperforms prior work on prompt-based tuning of VLMs. We release the benchmark, consisting of 14 datasets at https://github.com/cvl-umass/AdaptCLIPZS , which will contribute to future research in zero-shot recognition.

Aaron Sun, Oindrila Saha, Subhransu Maji

Since the advent of controllable image generation, increasingly rich modes of control have enabled greater customization and accessibility for everyday users. Zero-shot, identity-preserving models such as Insert Anything and OminiControl now support applications like virtual try-on without requiring additional fine-tuning. While these models may be fitting for humans and rigid everyday objects, they still have limitations for non-rigid or fine-grained categories. These domains often lack accessible, high-quality data -- especially videos or multi-view observations of the same subject -- making them difficult both to evaluate and to improve upon. Yet, such domains are essential for moving beyond content creation toward applications that demand accuracy and fine detail. Birds are an excellent domain for this task: they exhibit high diversity, require fine-grained cues for identification, and come in a wide variety of poses. We introduce the NABirds Look-Alikes (NABLA) dataset, consisting of 4,759 expert-curated image pairs. Together with 1,073 pairs collected from multi-image observations on iNaturalist and a small set of videos, this forms a benchmark for evaluating identity-preserving generation of birds. We show that state-of-the-art baselines fail to maintain identity on this dataset, and we demonstrate that training on images grouped by species, age, and sex -- used as a proxy for identity -- substantially improves performance on both seen and unseen species.

Oindrila Saha, Logan Lawrence, Grant Van Horn et al.

Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the structure of the language space in this context. We propose GTA-CLIP, a novel technique that incorporates supervision from language models for joint transduction in language and vision spaces. Our approach is iterative and consists of three steps: (i) incrementally exploring the attribute space by querying language models, (ii) an attribute-augmented transductive inference procedure, and (iii) fine-tuning the language and vision encoders based on inferred labels within the dataset. Through experiments with CLIP encoders, we demonstrate that GTA-CLIP, yields an average performance improvement of 8.6% and 3.7% across 12 datasets and 3 encoders, over CLIP and transductive CLIP respectively in the zero-shot setting. We also observe similar improvements in a few-shot setting. We present ablation studies that demonstrate the value of each step and visualize how the vision and language spaces evolve over iterations driven by the transductive learning. Code is released at https://github.com/cvl-umass/GTA-CLIP

Sandeep Mishra, Oindrila Saha, Alan C. Bovik

Motion-preserved video editing is crucial for creators, particularly in scenarios that demand flexibility in both the structure and semantics of swapped objects. Despite its potential, this area remains underexplored. Existing diffusion-based editing methods excel in structure-preserving tasks, using dense guidance signals to ensure content integrity. While some recent methods attempt to address structure-variable editing, they often suffer from issues such as temporal inconsistency, subject identity drift, and the need for human intervention. To address these challenges, we introduce VidMP3, a novel approach that leverages pose and position priors to learn a generalized motion representation from source videos. Our method enables the generation of new videos that maintain the original motion while allowing for structural and semantic flexibility. Both qualitative and quantitative evaluations demonstrate the superiority of our approach over existing methods. The code will be made publicly available at https://github.com/sandeep-sm/VidMP3.

Oindrila Saha, Aditya Kusupati, Harsha Vardhan Simhadri et al.

Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps. These require large working memory and are thus unsuitable for deployment on resource-constrained devices typically used for inference on the edge. Aggressively downsampling the images via pooling or strided convolutions can address the problem but leads to a significant decrease in accuracy due to gross aggregation of the feature map by standard pooling operators. In this paper, we introduce RNNPool, a novel pooling operator based on Recurrent Neural Networks (RNNs), that efficiently aggregates features over large patches of an image and rapidly downsamples activation maps. Empirical evaluation indicates that an RNNPool layer can effectively replace multiple blocks in a variety of architectures such as MobileNets, DenseNet when applied to standard vision tasks like image classification and face detection. That is, RNNPool can significantly decrease computational complexity and peak memory usage for inference while retaining comparable accuracy. We use RNNPool with the standard S3FD architecture to construct a face detection method that achieves state-of-the-art MAP for tiny ARM Cortex-M4 class microcontrollers with under 256 KB of RAM. Code is released at https://github.com/Microsoft/EdgeML.

Xiaohong Liu, Xiongkuo Min, Guangtao Zhai et al.

This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC). The challenge is divided into the image track and the video track. The image track uses the AIGIQA-20K, which contains 20,000 AI-Generated Images (AIGIs) generated by 15 popular generative models. The image track has a total of 318 registered participants. A total of 1,646 submissions are received in the development phase, and 221 submissions are received in the test phase. Finally, 16 participating teams submitted their models and fact sheets. The video track uses the T2VQA-DB, which contains 10,000 AI-Generated Videos (AIGVs) generated by 9 popular Text-to-Video (T2V) models. A total of 196 participants have registered in the video track. A total of 991 submissions are received in the development phase, and 185 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. Some methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on AIGC.

Logan Lawrence, Oindrila Saha, Megan Wei et al. · mit

Despite the renewed interest in zero-shot visual classification due to the rise of Multimodal Large Language Models (MLLMs), the problem of evaluating free-form responses of auto-regressive models remains a persistent challenge. Most existing works focus on language-only tasks or don't consider Multiple Choice Questions (MCQs) beyond 5-way options, both of which are critical capabilities to solve tasks in Fine-Grained Visual Classification (FGVC) where choice counts are in the hundreds to thousands and the choices are highly related. Furthermore, in this highly multi-way MCQ setting it is not clear how to extend LLM choice extraction to retrieval-based problems, where computing probabilities over the choice set is computationally costly. In this work we investigate nlg2choice, a simple two-stage method which first asks the MLLM an open-ended question for the task with minimal constraints, then uses text-only constrained decoding to predict the most likely choice. In retrieval settings, we compute the probability of the constrained response taking that choice with an early stopping method to significantly improve throughput. Our results show improvement over a suite of seven fine-grained visual datasets when evaluating in terms of classification and retrieval, and show that this performance holds over the various ways that users of LLMs can implement tasks in natural language.

Oindrila Saha, Vojtech Krs, Radomir Mech et al.

We present SIGMA-GEN, a unified framework for multi-identity preserving image generation. Unlike prior approaches, SIGMA-GEN is the first to enable single-pass multi-subject identity-preserved generation guided by both structural and spatial constraints. A key strength of our method is its ability to support user guidance at various levels of precision -- from coarse 2D or 3D boxes to pixel-level segmentations and depth -- with a single model. To enable this, we introduce SIGMA-SET27K, a novel synthetic dataset that provides identity, structure, and spatial information for over 100k unique subjects across 27k images. Through extensive evaluation we demonstrate that SIGMA-GEN achieves state-of-the-art performance in identity preservation, image generation quality, and speed. Code and visualizations at https://oindrilasaha.github.io/SIGMA-Gen/

Mahmudul Hasan, Sadia Ruhama, Sabrina Tajnim Sithi et al.

Deepfake videos, produced through advanced artificial intelligence methods now a days, pose a new challenge to the truthfulness of the digital media. As Deepfake becomes more convincing day by day, detecting them requires advanced methods capable of identifying subtle inconsistencies. The primary motivation of this paper is to recognize deepfake videos using deep learning techniques, specifically by using convolutional neural networks. Deep learning excels in pattern recognition, hence, makes it an ideal approach for detecting the intricate manipulations in deepfakes. In this paper, we consider using MTCNN as a face detector and EfficientNet-B5 as encoder model to predict if a video is deepfake or not. We utilize training and evaluation dataset from Kaggle DFDC. The results shows that our deepfake detection model acquired 42.78% log loss, 93.80% AUC and 86.82% F1 score on kaggle's DFDC dataset.

Sandeep Mishra, Oindrila Saha, Alan C. Bovik

3D generation guided by text-to-image diffusion models enables the creation of visually compelling assets. However previous methods explore generation based on image or text. The boundaries of creativity are limited by what can be expressed through words or the images that can be sourced. We present YouDream, a method to generate high-quality anatomically controllable animals. YouDream is guided using a text-to-image diffusion model controlled by 2D views of a 3D pose prior. Our method generates 3D animals that are not possible to create using previous text-to-3D generative methods. Additionally, our method is capable of preserving anatomic consistency in the generated animals, an area where prior text-to-3D approaches often struggle. Moreover, we design a fully automated pipeline for generating commonly found animals. To circumvent the need for human intervention to create a 3D pose, we propose a multi-agent LLM that adapts poses from a limited library of animal 3D poses to represent the desired animal. A user study conducted on the outcomes of YouDream demonstrates the preference of the animal models generated by our method over others. Turntable results and code are released at https://youdream3d.github.io/

Abhishek Sureddy, Dishant Padalia, Nandhinee Periyakaruppa et al.

Recent work has identified substantial disparities in generated images of different geographic regions, including stereotypical depictions of everyday objects like houses and cars. However, existing measures for these disparities have been limited to either human evaluations, which are time-consuming and costly, or automatic metrics evaluating full images, which are unable to attribute these disparities to specific parts of the generated images. In this work, we introduce a new set of metrics, Decomposed Indicators of Disparities in Image Generation (Decomposed-DIG), that allows us to separately measure geographic disparities in the depiction of objects and backgrounds in generated images. Using Decomposed-DIG, we audit a widely used latent diffusion model and find that generated images depict objects with better realism than backgrounds and that backgrounds in generated images tend to contain larger regional disparities than objects. We use Decomposed-DIG to pinpoint specific examples of disparities, such as stereotypical background generation in Africa, struggling to generate modern vehicles in Africa, and unrealistically placing some objects in outdoor settings. Informed by our metric, we use a new prompting structure that enables a 52% worst-region improvement and a 20% average improvement in generated background diversity.

Sandeep Mishra, Oindrila Saha, Alan C. Bovik

Recent advancements in text-to-3D generation have demonstrated the ability to generate high quality 3D assets. However while generating animals these methods underperform, often portraying inaccurate anatomy and geometry. Towards ameliorating this defect, we present C3DAG, a novel pose-Controlled text-to-3D Animal Generation framework which generates a high quality 3D animal consistent with a given pose. We also introduce an automatic 3D shape creator tool, that allows dynamic pose generation and modification via a web-based tool, and that generates a 3D balloon animal using simple geometries. A NeRF is then initialized using this 3D shape using depth-controlled SDS. In the next stage, the pre-trained NeRF is fine-tuned using quadruped-pose-controlled SDS. The pipeline that we have developed not only produces geometrically and anatomically consistent results, but also renders highly controlled 3D animals, unlike prior methods which do not allow fine-grained pose control.

Oindrila Saha, Zezhou Cheng, Subhransu Maji

Advances in generative modeling based on GANs has motivated the community to find their use beyond image generation and editing tasks. In particular, several recent works have shown that GAN representations can be re-purposed for discriminative tasks such as part segmentation, especially when training data is limited. But how do these improvements stack-up against recent advances in self-supervised learning? Motivated by this we present an alternative approach based on contrastive learning and compare their performance on standard few-shot part segmentation benchmarks. Our experiments reveal that not only do the GAN-based approach offer no significant performance advantage, their multi-step training is complex, nearly an order-of-magnitude slower, and can introduce additional bias. These experiments suggest that the inductive biases of generative models, such as their ability to disentangle shape and texture, are well captured by standard feed-forward networks trained using contrastive learning. These experiments suggest that the inductive biases present in current generative models, such as their ability to disentangle shape and texture, are well captured by standard feed-forward networks trained using contrastive learning.

Sandeep Mishra, Oindrila Saha

State-of-the-art saliency prediction methods develop upon model architectures or loss functions; while training to generate one target saliency map. However, publicly available saliency prediction datasets can be utilized to create more information for each stimulus than just a final aggregate saliency map. This information when utilized in a biologically inspired fashion can contribute in better prediction performance without the use of models with huge number of parameters. In this light, we propose to extract and use the statistics of (a) region specific saliency and (b) temporal order of fixations, to provide additional context to our network. We show that extra supervision using spatially or temporally sequenced fixations results in achieving better performance in saliency prediction. Further, we also design novel architectures for utilizing this extra information and show that it achieves superior performance over a base model which is devoid of extra supervision. We show that our best method outperforms previous state-of-the-art methods with 50-80% fewer parameters. We also show that our models perform consistently well across all evaluation metrics unlike prior methods.

Oindrila Saha, Rachana Sathish, Debdoot Sheet

Diabetic retinopathy (DR) is the most common form of diabetic eye disease. Retinopathy can affect all diabetic patients and becomes particularly dangerous, increasing the risk of blindness, if it is left untreated. The success rate of its curability solemnly depends on diagnosis at an early stage. The development of automated computer aided disease diagnosis tools could help in faster detection of symptoms with a wider reach and reasonable cost. This paper proposes a method for the automated segmentation of retinal lesions and optic disk in fundus images using a deep fully convolutional neural network for semantic segmentation. This trainable segmentation pipeline consists of an encoder network, a corresponding decoder network followed by pixel-wise classification to segment microaneurysms, hemorrhages, hard exudates, soft exudates, optic disk from background. The network was trained using Binary cross entropy criterion with Sigmoid as the last layer, while during an additional SoftMax layer was used for boosting response of single class. The performance of the proposed method is evaluated using sensitivity, positive prediction value (PPV) and accuracy as the metrices. Further, the position of the Optic disk is localised using the segmented output map.