Haokui Zhang

Haokui Zhang, Wenze Hu, Xiaoyu Wang

Recently, vision transformers started to show impressive results which outperform large convolution based models significantly. However, in the area of small models for mobile or resource constrained devices, ConvNet still has its own advantages in both performance and model complexity. We propose ParC-Net, a pure ConvNet based backbone model that further strengthens these advantages by fusing the merits of vision transformers into ConvNets. Specifically, we propose position aware circular convolution (ParC), a light-weight convolution op which boasts a global receptive field while producing location sensitive features as in local convolutions. We combine the ParCs and squeeze-exictation ops to form a meta-former like model block, which further has the attention mechanism like transformers. The aforementioned block can be used in plug-and-play manner to replace relevant blocks in ConvNets or transformers. Experiment results show that the proposed ParC-Net achieves better performance than popular light-weight ConvNets and vision transformer based models in common vision tasks and datasets, while having fewer parameters and faster inference speed. For classification on ImageNet-1k, ParC-Net achieves 78.6% top-1 accuracy with about 5.0 million parameters, saving 11% parameters and 13% computational cost but gaining 0.2% higher accuracy and 23% faster inference speed (on ARM based Rockchip RK3288) compared with MobileViT, and uses only 0.5 times parameters but gaining 2.7% accuracy compared with DeIT. On MS-COCO object detection and PASCAL VOC segmentation tasks, ParC-Net also shows better performance. Source code is available at https://github.com/hkzhang91/ParC-Net

Yun Yi, Haokui Zhang, Wenze Hu et al.

With the wide and deep adoption of deep learning models in real applications, there is an increasing need to model and learn the representations of the neural networks themselves. These models can be used to estimate attributes of different neural network architectures such as the accuracy and latency, without running the actual training or inference tasks. In this paper, we propose a neural architecture representation model that can be used to estimate these attributes holistically. Specifically, we first propose a simple and effective tokenizer to encode both the operation and topology information of a neural network into a single sequence. Then, we design a multi-stage fusion transformer to build a compact vector representation from the converted sequence. For efficient model training, we further propose an information flow consistency augmentation and correspondingly design an architecture consistency loss, which brings more benefits with less augmentation samples compared with previous random augmentation strategies. Experiment results on NAS-Bench-101, NAS-Bench-201, DARTS search space and NNLQP show that our proposed framework can be used to predict the aforementioned latency and accuracy attributes of both cell architectures and whole deep neural networks, and achieves promising performance. Code is available at https://github.com/yuny220/NAR-Former.

Yun Yi, Haokui Zhang, Rong Xiao et al.

As more deep learning models are being applied in real-world applications, there is a growing need for modeling and learning the representations of neural networks themselves. An efficient representation can be used to predict target attributes of networks without the need for actual training and deployment procedures, facilitating efficient network deployment and design. Recently, inspired by the success of Transformer, some Transformer-based representation learning frameworks have been proposed and achieved promising performance in handling cell-structured models. However, graph neural network (GNN) based approaches still dominate the field of learning representation for the entire network. In this paper, we revisit Transformer and compare it with GNN to analyse their different architecture characteristics. We then propose a modified Transformer-based universal neural network representation learning model NAR-Former V2. It can learn efficient representations from both cell-structured networks and entire networks. Specifically, we first take the network as a graph and design a straightforward tokenizer to encode the network into a sequence. Then, we incorporate the inductive representation learning capability of GNN into Transformer, enabling Transformer to generalize better when encountering unseen architecture. Additionally, we introduce a series of simple yet effective modifications to enhance the ability of the Transformer in learning representation from graph structures. Our proposed method surpasses the GNN-based method NNLP by a significant margin in latency estimation on the NNLQP dataset. Furthermore, regarding accuracy prediction on the NASBench101 and NASBench201 datasets, our method achieves highly comparable performance to other state-of-the-art methods.

Xizhe Xue, Haokui Zhang, Haizhao Jing et al.

Data-hungry HSI classification methods require high-quality labeled HSIs, which are often costly to obtain. This characteristic limits the performance potential of data-driven methods when dealing with limited annotated samples. Bridging the domain gap between data acquired from different sensors allows us to utilize abundant labeled data across sensors to break this bottleneck. In this paper, we propose a novel Attention-Gated Tuning (AGT) strategy and a triplet-structured transformer model, Tri-Former, to address this issue. The AGT strategy serves as a bridge, allowing us to leverage existing labeled HSI datasets, even RGB datasets to enhance the performance on new HSI datasets with limited samples. Instead of inserting additional parameters inside the basic model, we train a lightweight auxiliary branch that takes intermediate features as input from the basic model and makes predictions. The proposed AGT resolves conflicts between heterogeneous and even cross-modal data by suppressing the disturbing information and enhances the useful information through a soft gate. Additionally, we introduce Tri-Former, a triplet-structured transformer with a spectral-spatial separation design that enhances parameter utilization and computational efficiency, enabling easier and flexible fine-tuning. Comparison experiments conducted on three representative HSI datasets captured by different sensors demonstrate the proposed Tri-Former achieves better performance compared to several state-of-the-art methods. Homologous, heterologous and cross-modal tuning experiments verified the effectiveness of the proposed AGT. Code has been released at: \href{https://github.com/Cecilia-xue/AGT}{https://github.com/Cecilia-xue/AGT}.

Ruihan Xu, Haokui Zhang, Wenze Hu et al.

Transformers have shown great potential in various computer vision tasks. By borrowing design concepts from transformers, many studies revolutionized CNNs and showed remarkable results. This paper falls in this line of studies. Specifically, we propose a new convolutional neural network, ParCNetV2, that extends position-aware circular convolution (ParCNet) with oversized convolutions and bifurcate gate units to enhance attention. The oversized convolution employs a kernel with twice the input size to model long-range dependencies through a global receptive field. Simultaneously, it achieves implicit positional encoding by removing the shift-invariant property from convolution kernels, i.e., the effective kernels at different spatial locations are different when the kernel size is twice as large as the input size. The bifurcate gate unit implements an attention mechanism similar to self-attention in transformers. It is applied through element-wise multiplication of the two branches, one serves as feature transformation while the other serves as attention weights. Additionally, we introduce a uniform local-global convolution block to unify the design of the early and late stage convolution blocks. Extensive experiments demonstrate the superiority of our method over other convolutional neural networks and hybrid models that combine CNNs and transformers. Code will be released.

Haokui Zhang, Congyang Ou, Dawei Yan et al.

Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristics constructed based on inter-visual-token similarity or cross-modal visual-text similarity, which gives rise to certain limitations in compression performance and practical deployment. In contrast, we propose PIO-FVLM from the perspective of inference objectives, which transforms visual token compression into preserving output result invariance and selects tokens primarily by their importance to this goal. Specially, vision tokens are reordered with the guidance of token-level gradient saliency generated by our designed layer-local proxy loss, a coarse constraint from the current layer to the final result. Then the most valuable vision tokens are selected following the non-maximum suppression (NMS) principle. The proposed PIO-FVLM is training-free and compatible with FlashAttention, friendly to practical application and deployment. It can be deployed independently as an encoder-free method, or combined with encoder compression approaches like VisionZip for use as an encoder-involved method. On LLaVA-Next-7B, PIO-FVLM retains just 11.1% of visual tokens but maintains 97.2% of the original performance, with a 2.67$\times$ prefill speedup, 2.11$\times$ inference speedup, 6.22$\times$ lower FLOPs, and 6.05$\times$ reduced KV Cache overhead. Our code is available at https://github.com/ocy1/PIO-FVLM.

Guoting Wei, Xia Yuan, Yu Liu et al.

Aerial object detection plays a crucial role in numerous applications. However, most existing methods focus on detecting predefined object categories, limiting their applicability in real-world open scenarios. In this paper, we extend aerial object detection to open scenarios through image-text collaboration and propose RT-OVAD, the first real-time open-vocabulary detector for aerial scenes. Specifically, we first introduce an image-to-text alignment loss to replace the conventional category regression loss, thereby eliminating category constraints. Next, we propose a lightweight image-text collaboration strategy comprising an image-text collaboration encoder and a text-guided decoder. The encoder simultaneously enhances visual features and refines textual embeddings, while the decoder guides object queries to focus on class-relevant image features. This design further improves detection accuracy without incurring significant computational overhead. Extensive experiments demonstrate that RT-OVAD consistently outperforms existing state-of-the-art methods across open-vocabulary, zero-shot, and traditional closed-set detection tasks. For instance, on the open-vocabulary aerial detection benchmarks DIOR, DOTA-v2.0, and LAE-80C, RT-OVAD achieves 87.7 AP$_{50}$, 53.8 mAP, and 23.7 mAP, respectively, surpassing the previous state-of-the-art (LAE-DINO) by 2.2, 7.0, and 3.5 points. In addition, RT-OVAD achieves an inference speed of 34 FPS on an RTX 4090 GPU, approximately three times faster than LAE-DINO (10 FPS), meeting the real-time detection requirements of diverse applications. The code will be released at https://github.com/GT-Wei/RT-OVAD.

Shengqin Jiang, Yaoyu Fang, Haokui Zhang et al.

Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data. However, this method faces two major challenges for video task: substantial computing resources from loading teacher model and limited replay capability from performance-limited teacher model. To address these problems, we first propose a knowledge distillation-free framework for rehearsal-based video incremental learning called \textit{Teacher Agent}. Instead of loading parameter-heavy teacher networks, we introduce an agent generator that is either parameter-free or uses only a few parameters to obtain accurate and reliable soft labels. This method not only greatly reduces the computing requirement but also circumvents the problem of knowledge misleading caused by inaccurate predictions of the teacher model. Moreover, we put forward a self-correction loss which provides an effective regularization signal for the review of old knowledge, which in turn alleviates the problem of catastrophic forgetting. Further, to ensure that the samples in the memory buffer are memory-efficient and representative, we introduce a unified sampler for rehearsal-based video incremental learning to mine fixed-length key video frames. Interestingly, based on the proposed strategies, the network exhibits a high level of robustness against spatial resolution reduction when compared to the baseline. Extensive experiments demonstrate the advantages of our method, yielding significant performance improvements while utilizing only half the spatial resolution of video clips as network inputs in the incremental phases.

Dawei Yan, Pengcheng Li, Yang Li et al.

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the connector and enhancing the language model component, while neglecting improvements to the vision encoder itself. In contrast, we propose Text Guided LLaVA (TG-LLaVA) in this paper, which optimizes VLMs by guiding the vision encoder with text, offering a new and orthogonal optimization direction. Specifically, inspired by the purpose-driven logic inherent in human behavior, we use learnable latent embeddings as a bridge to analyze textual instruction and add the analysis results to the vision encoder as guidance, refining it. Subsequently, another set of latent embeddings extracts additional detailed text-guided information from high-resolution local patches as auxiliary information. Finally, with the guidance of text, the vision encoder can extract text-related features, similar to how humans focus on the most relevant parts of an image when considering a question. This results in generating better answers. Experiments on various datasets validate the effectiveness of the proposed method. Remarkably, without the need for additional training data, our propsoed method can bring more benefits to the baseline (LLaVA-1.5) compared with other concurrent methods. Furthermore, the proposed method consistently brings improvement in different settings.

Shengqin Jiang, Xiaoran Feng, Yuankai Qi et al.

Few-shot class-incremental learning (FSCIL) seeks to continuously learn new classes from very limited samples while preserving previously acquired knowledge. Traditional methods often utilize a frozen pre-trained feature extractor to generate static class prototypes, which suffer from the inherent representation bias of the backbone. While recent prompt-based tuning methods attempt to adapt the backbone via minimal parameter updates, given the constraint of extreme data scarcity, the model's capacity to assimilate novel information and substantively enhance its global discriminative power is inherently limited. In this paper, we propose a novel shift in perspective: freezing the feature extractor while fine-tuning the prototypes. We argue that the primary challenge in FSCIL is not feature acquisition, but rather the optimization of decision regions within a static, high-quality feature space. To this end, we introduce an efficient prototype fine-tuning framework that evolves static centroids into dynamic, learnable components. The framework employs a dual-calibration method consisting of class-specific and task-aware offsets. These components function synergistically to improve the discriminative capacity of prototypes for ongoing incremental classes. Extensive results demonstrate that our method attains superior performance across multiple benchmarks while requiring minimal learnable parameters.

Haizhao Jing, Liuwei Wan, Xizhe Xue et al.

Recently, the Vision Transformer (ViT) model has replaced the classical Convolutional Neural Network (ConvNet) in various computer vision tasks due to its superior performance. Even in hyperspectral image (HSI) classification field, ViT-based methods also show promising potential. Nevertheless, ViT encounters notable difficulties in processing HSI data. Its self-attention mechanism, which exhibits quadratic complexity, escalates computational costs. Additionally, ViT's substantial demand for training samples does not align with the practical constraints posed by the expensive labeling of HSI data. To overcome these challenges, we propose a 3D relational ConvNet named 3D-RCNet, which inherits both strengths of ConvNet and ViT, resulting in high performance in HSI classification. We embed the self-attention mechanism of Transformer into the convolutional operation of ConvNet to design 3D relational convolutional operation and use it to build the final 3D-RCNet. The proposed 3D-RCNet maintains the high computational efficiency of ConvNet while enjoying the flexibility of ViT. Additionally, the proposed 3D relational convolutional operation is a plug-and-play operation, which can be inserted into previous ConvNet-based HSI classification methods seamlessly. Empirical evaluations on three representative benchmark HSI datasets show that the proposed model outperforms previous ConvNet-based and ViT-based HSI approaches.

Haokui Zhang, Wenze Hu, Xiaoyu Wang

Currently, one main research line in designing a more efficient vision transformer is reducing the computational cost of self attention modules by adopting sparse attention or using local attention windows. In contrast, we propose a different approach that aims to improve the performance of transformer-based architectures by densifying the attention pattern. Specifically, we proposed forward cross attention for hybrid vision transformer (FcaFormer), where tokens from previous blocks in the same stage are secondary used. To achieve this, the FcaFormer leverages two innovative components: learnable scale factors (LSFs) and a token merge and enhancement module (TME). The LSFs enable efficient processing of cross tokens, while the TME generates representative cross tokens. By integrating these components, the proposed FcaFormer enhances the interactions of tokens across blocks with potentially different semantics, and encourages more information flows to the lower levels. Based on the forward cross attention (Fca), we have designed a series of FcaFormer models that achieve the best trade-off between model size, computational cost, memory cost, and accuracy. For example, without the need for knowledge distillation to strengthen training, our FcaFormer achieves 83.1% top-1 accuracy on Imagenet with only 16.3 million parameters and about 3.6 billion MACs. This saves almost half of the parameters and a few computational costs while achieving 0.7% higher accuracy compared to distilled EfficientFormer.

Tao Yang, Haokui Zhang, Wenze Hu et al.

Transformer models have made tremendous progress in various fields in recent years. In the field of computer vision, vision transformers (ViTs) also become strong alternatives to convolutional neural networks (ConvNets), yet they have not been able to replace ConvNets since both have their own merits. For instance, ViTs are good at extracting global features with attention mechanisms while ConvNets are more efficient in modeling local relationships due to their strong inductive bias. A natural idea that arises is to combine the strengths of both ConvNets and ViTs to design new structures. In this paper, we propose a new basic neural network operator named position-aware circular convolution (ParC) and its accelerated version Fast-ParC. The ParC operator can capture global features by using a global kernel and circular convolution while keeping location sensitiveness by employing position embeddings. Our Fast-ParC further reduces the O(n2) time complexity of ParC to O(n log n) using Fast Fourier Transform. This acceleration makes it possible to use global convolution in the early stages of models with large feature maps, yet still maintains the overall computational cost comparable with using 3x3 or 7x7 kernels. The proposed operation can be used in a plug-and-play manner to 1) convert ViTs to pure-ConvNet architecture to enjoy wider hardware support and achieve higher inference speed; 2) replacing traditional convolutions in the deep stage of ConvNets to improve accuracy by enlarging the effective receptive field. Experiment results show that our ParC op can effectively enlarge the receptive field of traditional ConvNets, and adopting the proposed op benefits both ViTs and ConvNet models on all three popular vision tasks, image classification, object

Junjie Li, Congyang Ou, Haokui Zhang et al.

Recently, diffusion models bring novel insights for Pan-sharpening and notably boost fusion precision. However, most existing models perform diffusion in the pixel space and train distinct models for different multispectral (MS) imagery, suffering from high latency and sensor-specific limitations. In this paper, we present SALAD-Pan, a sensor-agnostic latent space diffusion method for efficient pansharpening. Specifically, SALAD-Pan trains a band-wise single-channel VAE to encode high-resolution multispectral (HRMS) into compact latent representations, supporting MS images with various channel counts and establishing a basis for acceleration. Then spectral physical properties, along with PAN and MS images, are injected into the diffusion backbone through unidirectional and bidirectional interactive control structures respectively, achieving high-precision fusion in the diffusion process. Finally, a lightweight cross-spectral attention module is added to the central layer of diffusion model, reinforcing spectral connections to boost spectral consistency and further elevate fusion precision. Experimental results on GaoFen-2, QuickBird, and WorldView-3 demonstrate that SALAD-Pan outperforms state-of-the-art diffusion-based methods across all three datasets, attains a 2-3x inference speedup, and exhibits robust zero-shot (cross-sensor) capability.

Shengqin Jiang, Tianqi Kong, Yuankai Qi et al.

Prompt-based continual learning methods fine-tune only a small set of additional learnable parameters while keeping the pre-trained model's parameters frozen. It enables efficient adaptation to new tasks while mitigating the risk of catastrophic forgetting. These methods typically attach one independent task-specific prompt to each layer of pre-trained models to locally modulate its features, ensuring that the layer's representation aligns with the requirements of the new task. However, although introducing learnable prompts independently at each layer provides high flexibility for adapting to new tasks, this overly flexible tuning could make certain layers susceptible to unnecessary updates. As all prompts till the current task are added together as a final prompt for all seen tasks, the model may easily overwrite feature representations essential to previous tasks, which increases the risk of catastrophic forgetting. To address this issue, we propose a novel hierarchical layer-grouped prompt tuning method for continual learning. It improves model stability in two ways: (i) Layers in the same group share roughly the same prompts, which are adjusted by position encoding. This helps preserve the intrinsic feature relationships and propagation pathways of the pre-trained model within each group. (ii) It utilizes a single task-specific root prompt to learn to generate sub-prompts for each layer group. In this way, all sub-prompts are conditioned on the same root prompt, enhancing their synergy and reducing independence. Extensive experiments across four benchmarks demonstrate that our method achieves favorable performance compared with several state-of-the-art methods.

Qiang Li, Qingsen Yan, Haojian Huang et al.

With the rapid advancements in Artificial Intelligence Generated Image (AGI) technology, the accurate assessment of their quality has become an increasingly vital requirement. Prevailing methods typically rely on cross-modal models like CLIP or BLIP to evaluate text-image alignment and visual quality. However, when applied to AGIs, these methods encounter two primary challenges: semantic misalignment and details perception missing. To address these limitations, we propose Text-Visual Semantic Constrained AI-Generated Image Quality Assessment (SC-AGIQA), a unified framework that leverages text-visual semantic constraints to significantly enhance the comprehensive evaluation of both text-image consistency and perceptual distortion in AI-generated images. Our approach integrates key capabilities from multiple models and tackles the aforementioned challenges by introducing two core modules: the Text-assisted Semantic Alignment Module (TSAM), which leverages Multimodal Large Language Models (MLLMs) to bridge the semantic gap by generating an image description and comparing it against the original prompt for a refined consistency check, and the Frequency-domain Fine-Grained Degradation Perception Module (FFDPM), which draws inspiration from Human Visual System (HVS) properties by employing frequency domain analysis combined with perceptual sensitivity weighting to better quantify subtle visual distortions and enhance the capture of fine-grained visual quality details in images. Extensive experiments conducted on multiple benchmark datasets demonstrate that SC-AGIQA outperforms existing state-of-the-art methods. The code is publicly available at https://github.com/mozhu1/SC-AGIQA.

Guoting Wei, Yu Liu, Xia Yuan et al.

In recent years, language-guided open-set aerial object detection has gained significant attention due to its better alignment with real-world application needs. However, due to limited datasets, most existing language-guided methods primarily focus on vocabulary-level descriptions, which fail to meet the demands of fine-grained open-world detection. To address this limitation, we propose constructing a large-scale language-guided open-set aerial detection dataset, encompassing three levels of language guidance: from words to phrases, and ultimately to sentences. Centered around an open-source large vision-language model and integrating image-operation-based preprocessing with BERT-based postprocessing, we present the OS-W2S Label Engine, an automatic annotation pipeline capable of handling diverse scene annotations for aerial images. Using this label engine, we expand existing aerial detection datasets with rich textual annotations and construct a novel benchmark dataset, called MI-OAD, addressing the limitations of current remote sensing grounding data and enabling effective language-guided open-set aerial detection. Specifically, MI-OAD contains 163,023 images and 2 million image-caption pairs, approximately 40 times larger than comparable datasets. To demonstrate the effectiveness and quality of MI-OAD, we evaluate three representative tasks. On language-guided open-set aerial detection, training on MI-OAD lifts Grounding DINO by +31.1 AP$_{50}$ and +34.7 Recall@10 with sentence-level inputs under zero-shot transfer. Moreover, using MI-OAD for pre-training yields state-of-the-art performance on multiple existing open-vocabulary aerial detection and remote sensing visual grounding benchmarks, validating both the effectiveness of the dataset and the high quality of its OS-W2S annotations. More details are available at https://github.com/GT-Wei/MI-OAD.

Ruihan Xu, Haokui Zhang, Yaowei Wang et al.

The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and transformers have shown promising performance in representing neural architectures. However, each of both methods has its disadvantages. GNNs lack the capabilities to represent complicated features, while transformers face poor generalization when the depth of architecture grows. To mitigate the above issues, we rethink neural architecture topology and show that sibling nodes are pivotal while overlooked in previous research. We thus propose a novel predictor leveraging the strengths of GNNs and transformers to learn the enhanced topology. We introduce a novel token mixer that considers siblings, and a new channel mixer named bidirectional graph isomorphism feed-forward network. Our approach consistently achieves promising performance in both accuracy and latency prediction, providing valuable insights for learning Directed Acyclic Graph (DAG) topology. The code is available at https://github.com/XuRuihan/NNFormer.

Lijie Tao, Haokui Zhang, Haizhao Jing et al.

Recently, the remarkable success of ChatGPT has sparked a renewed wave of interest in artificial intelligence (AI), and the advancements in visual language models (VLMs) have pushed this enthusiasm to new heights. Differring from previous AI approaches that generally formulated different tasks as discriminative models, VLMs frame tasks as generative models and align language with visual information, enabling the handling of more challenging problems. The remote sensing (RS) field, a highly practical domain, has also embraced this new trend and introduced several VLM-based RS methods that have demonstrated promising performance and enormous potential. In this paper, we first review the fundamental theories related to VLM, then summarize the datasets constructed for VLMs in remote sensing and the various tasks they addressed. Finally, we categorize the improvement methods into three main parts according to the core components of VLMs and provide a detailed introduction and comparison of these methods. A project associated with this review has been created at https://github.com/taolijie11111/VLMs-in-RS-review.

Yang Zhou, Junjie Li, CongYang Ou et al.

Due to its extensive applications, aerial image object detection has long been a hot topic in computer vision. In recent years, advancements in Unmanned Aerial Vehicles (UAV) technology have further propelled this field to new heights, giving rise to a broader range of application requirements. However, traditional UAV aerial object detection methods primarily focus on detecting predefined categories, which significantly limits their applicability. The advent of cross-modal text-image alignment (e.g., CLIP) has overcome this limitation, enabling open-vocabulary object detection (OVOD), which can identify previously unseen objects through natural language descriptions. This breakthrough significantly enhances the intelligence and autonomy of UAVs in aerial scene understanding. This paper presents a comprehensive survey of OVOD in the context of UAV aerial scenes. We begin by aligning the core principles of OVOD with the unique characteristics of UAV vision, setting the stage for a specialized discussion. Building on this foundation, we construct a systematic taxonomy that categorizes existing OVOD methods for aerial imagery and provides a comprehensive overview of the relevant datasets. This structured review enables us to critically dissect the key challenges and open problems at the intersection of these fields. Finally, based on this analysis, we outline promising future research directions and application prospects. This survey aims to provide a clear road map and a valuable reference for both newcomers and seasoned researchers, fostering innovation in this rapidly evolving domain. We keep tracing related works at https://github.com/zhouyang2002/OVOD-in-UVA-imagery

Xizhe Xue, Haokui Zhang, Bei Fang et al.

Hyperspectral image (HSI) classification has been a hot topic for decides, as hyperspectral images have rich spatial and spectral information and provide strong basis for distinguishing different land-cover objects. Benefiting from the development of deep learning technologies, deep learning based HSI classification methods have achieved promising performance. Recently, several neural architecture search (NAS) algorithms have been proposed for HSI classification, which further improve the accuracy of HSI classification to a new level. In this paper, NAS and Transformer are combined for handling HSI classification task for the first time. Compared with previous work, the proposed method has two main differences. First, we revisit the search spaces designed in previous HSI classification NAS methods and propose a novel hybrid search space, consisting of the space dominated cell and the spectrum dominated cell. Compared with search spaces proposed in previous works, the proposed hybrid search space is more aligned with the characteristic of HSI data, that is, HSIs have a relatively low spatial resolution and an extremely high spectral resolution. Second, to further improve the classification accuracy, we attempt to graft the emerging transformer module on the automatically designed convolutional neural network (CNN) to add global information to local region focused features learned by CNN. Experimental results on three public HSI datasets show that the proposed method achieves much better performance than comparison approaches, including manually designed network and NAS based HSI classification methods. Especially on the most recently captured dataset Houston University, overall accuracy is improved by nearly 6 percentage points. Code is available at: https://github.com/Cecilia-xue/HyT-NAS.

Haokui Zhang, Ying Li, Hao Chen et al.

Recently, much attention has been spent on neural architecture search (NAS), aiming to outperform those manually-designed neural architectures on high-level vision recognition tasks. Inspired by the success, here we attempt to leverage NAS techniques to automatically design efficient network architectures for low-level image restoration tasks. In particular, we propose a memory-efficient hierarchical NAS (termed HiNAS) and apply it to two such tasks: image denoising and image super-resolution. HiNAS adopts gradient based search strategies and builds a flexible hierarchical search space, including the inner search space and outer search space. They are in charge of designing cell architectures and deciding cell widths, respectively. For the inner search space, we propose a layer-wise architecture sharing strategy (LWAS), resulting in more flexible architectures and better performance. For the outer search space, we design a cell-sharing strategy to save memory, and considerably accelerate the search speed. The proposed HiNAS method is both memory and computation efficient. With a single GTX1080Ti GPU, it takes only about 1 hour for searching for denoising network on the BSD-500 dataset and 3.5 hours for searching for the super-resolution structure on the DIV2K dataset. Experiments show that the architectures found by HiNAS have fewer parameters and enjoy a faster inference speed, while achieving highly competitive performance compared with state-of-the-art methods. Code is available at: https://github.com/hkzhang91/HiNAS

Haokui Zhang, Yu Liu, Bei Fang et al.

Hyperspectral image(HSI) classification has been improved with convolutional neural network(CNN) in very recent years. Being different from the RGB datasets, different HSI datasets are generally captured by various remote sensors and have different spectral configurations. Moreover, each HSI dataset only contains very limited training samples and thus it is prone to overfitting when using deep CNNs. In this paper, we first deliver a 3D asymmetric inception network, AINet, to overcome the overfitting problem. With the emphasis on spectral signatures over spatial contexts of HSI data, AINet can convey and classify the features effectively. In addition, the proposed data fusion transfer learning strategy is beneficial in boosting the classification performance. Extensive experiments show that the proposed approach beat all of the state-of-art methods on several HSI benchmarks, including Pavia University, Indian Pines and Kennedy Space Center(KSC). Code can be found at: https://github.com/UniLauX/AINet.

Haokui Zhang, Chunhua Shen, Ying Li et al.

Accuracy of depth estimation from static images has been significantly improved recently, by exploiting hierarchical features from deep convolutional neural networks (CNNs). Compared with static images, vast information exists among video frames and can be exploited to improve the depth estimation performance. In this work, we focus on exploring temporal information from monocular videos for depth estimation. Specifically, we take the advantage of convolutional long short-term memory (CLSTM) and propose a novel spatial-temporal CSLTM (ST-CLSTM) structure. Our ST-CLSTM structure can capture not only the spatial features but also the temporal correlations/consistency among consecutive video frames with negligible increase in computational cost. Additionally, in order to maintain the temporal consistency among the estimated depth frames, we apply the generative adversarial learning scheme and design a temporal consistency loss. The temporal consistency loss is combined with the spatial loss to update the model in an end-to-end fashion. By taking advantage of the temporal information, we build a video depth estimation framework that runs in real-time and generates visually pleasant results. Moreover, our approach is flexible and can be generalized to most existing depth estimation frameworks. Code is available at: https://tinyurl.com/STCLSTM

Xizhe Xue, Guoting Wei, Hao Chen et al.

The rapid evolution of Vision Language Models (VLMs) has catalyzed significant advancements in artificial intelligence, expanding research across various disciplines, including Earth Observation (EO). While VLMs have enhanced image understanding and data processing within EO, their applications have predominantly focused on image content description. This limited focus overlooks their potential in geographic and scientific regression tasks, which are essential for diverse EO applications. To bridge this gap, this paper introduces a novel benchmark dataset, called \textbf{REO-Instruct} to unify regression and generation tasks specifically for the EO domain. Comprising 1.6 million multimodal EO imagery and language pairs, this dataset is designed to support both biomass regression and image content interpretation tasks. Leveraging this dataset, we develop \textbf{REO-VLM}, a groundbreaking model that seamlessly integrates regression capabilities with traditional generative functions. By utilizing language-driven reasoning to incorporate scientific domain knowledge, REO-VLM goes beyond solely relying on EO imagery, enabling comprehensive interpretation of complex scientific attributes from EO data. This approach establishes new performance benchmarks and significantly enhances the capabilities of environmental monitoring and resource management.

Dawei Yan, Yang Li, Qing-Guo Chen et al.

Compared to single-turn dialogue, multi-turn dialogue involving multiple images better aligns with the needs of real-world human-AI interactions. Additionally, as training data, it provides richer contextual reasoning information, thereby guiding the model to achieve better performance. However, existing vision-language models (VLMs) primarily rely on single-turn dialogue training and evaluation benchmarks. In this paper, following the characteristics of human dialogue, such as focused topics and concise, clear content, we present MMCR (Multimodal Multi-turn Contextual Reasoning), a novel dataset comprising: (1) MMCR-310k -- the largest multi-image multi-turn instruction tuning dataset with 310K contextual dialogues, each covering 1-4 images and 4 or 8 dialogue turns; and (2) MMCR-Bench -- a diagnostic benchmark featuring dialogues, spanning 8 domains (Humanities, Natural, Science, Education, etc.) and 40 sub-topics. Extensive evaluations demonstrate that models fine-tuned with MMCR-310k achieve 5.2\% higher contextual accuracy on MMCR-Bench, while showing consistent improvements on existing benchmarks (+1.1\% on AI2D, +1.2\% on MMMU and MMVet). MMCR and prompt engineering will be released publicly.

Wei Dong, Yuan Sun, Yiting Yang et al.

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To address this limitation, we propose a novel PEFT approach inspired by Singular Value Decomposition (SVD) for representing the adaptation matrix. SVD decomposes a matrix into the product of a left unitary matrix, a diagonal matrix of scaling values, and a right unitary matrix. We utilize Householder transformations to construct orthogonal matrices that efficiently mimic the unitary matrices, requiring only a vector. The diagonal values are learned in a layer-wise manner, allowing them to flexibly capture the unique properties of each layer. This approach enables the generation of adaptation matrices with varying ranks across different layers, providing greater flexibility in adapting pre-trained models. Experiments on standard downstream vision tasks demonstrate that our method achieves promising fine-tuning performance.

Xizhe Xue, Yang Zhou, Dawei Yan et al.

Recently, the remarkable success of large language models (LLMs) has achieved a profound impact on the field of artificial intelligence. Numerous advanced works based on LLMs have been proposed and applied in various scenarios. Among them, video language models (VidLMs) are particularly widely used. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding application needs of underwater observation. To overcome this gap, we introduce UVLM, an under water observation benchmark which is build through a collaborative approach combining human expertise and AI models. To ensure data quality, we have conducted in-depth considerations from multiple perspectives. First, to address the unique challenges of underwater environments, we selected videos that represent typical underwater challenges including light variations, water turbidity, and diverse viewing angles to construct the dataset. Second, to ensure data diversity, the dataset covers a wide range of frame rates, resolutions, 419 classes of marine animals, and various static plants and terrains. Next, for task diversity, we adopted a structured design where observation targets are categorized into two major classes: biological and environmental. Each category includes content observation and change/action observation, totaling 20 distinct task types. Finally, we designed several challenging evaluation metrics to enable quantitative comparison and analysis of different methods. Experiments on two representative VidLMs demonstrate that fine-tuning VidLMs on UVLM significantly improves underwater world understanding while also showing potential for slight improvements on existing in-air VidLM benchmarks, such as VideoMME and Perception text. The dataset and prompt engineering will be released publicly.

Yiting Yang, Hao Luo, Yuan Sun et al.

A prevalent approach in Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViT) involves freezing the majority of the backbone parameters and solely learning low-rank adaptation weight matrices to accommodate downstream tasks. These low-rank matrices are commonly derived through the multiplication structure of down-projection and up-projection matrices, exemplified by methods such as LoRA and Adapter. In this work, we observe an approximate orthogonality among any two row or column vectors within any weight matrix of the backbone parameters; however, this property is absent in the vectors of the down/up-projection matrices. Approximate orthogonality implies a reduction in the upper bound of the model's generalization error, signifying that the model possesses enhanced generalization capability. If the fine-tuned down/up-projection matrices were to exhibit this same property as the pre-trained backbone matrices, could the generalization capability of fine-tuned ViTs be further augmented? To address this question, we propose an Approximately Orthogonal Fine-Tuning (AOFT) strategy for representing the low-rank weight matrices. This strategy employs a single learnable vector to generate a set of approximately orthogonal vectors, which form the down/up-projection matrices, thereby aligning the properties of these matrices with those of the backbone. Extensive experimental results demonstrate that our method achieves competitive performance across a range of downstream image classification tasks, confirming the efficacy of the enhanced generalization capability embedded in the down/up-projection matrices.

Feng Lin, Marco Chen, Haokui Zhang et al.

This paper investigates the role of attention heads in CLIP's image encoder. Building on interpretability studies, we conduct an exhaustive analysis and find that certain heads, distributed across layers, are detrimental to the resulting representations. To mitigate their impact, we propose a simple yet effective Attention Ablation Technique (AAT) that suppresses selected heads by directly manipulating their attention weights. By incorporating two complementary strategies tailored to different application scenarios, AAT enables the systematic identification and ablation of harmful heads with minimal overhead. Experiments show that AAT consistently improves downstream performance across diverse domains, boosting recall by up to 11.1% on cross-modal retrieval benchmarks. These results highlight that AAT can effectively refine large-scale VLMs with virtually no extra inference cost, while yielding semantically meaningful patterns that align with existing interpretability findings.

Haizhao Jing, Haokui Zhang, Zhenhao Shang et al.

Neural Architecture Representation Learning aims to transform network models into feature representations for predicting network attributes, playing a crucial role in deploying and designing networks for real-world applications. Recently, inspired by the success of transformers, transformer-based models integrated with Graph Neural Networks (GNNs) have achieved significant progress in representation learning. However, current methods still have some limitations. First, existing methods overlook hardware attribute information, which conflicts with the current trend of diversified deep learning hardware and limits the practical applicability of models. Second, current encoding approaches rely on static adjacency matrices to represent topological structures, failing to capture the structural differences between computational nodes, which ultimately compromises encoding effectiveness. In this paper, we introduce LeDG-Former, an innovative framework that addresses these limitations through the synergistic integration of language-based semantic embedding and dynamic graph representation learning. Specifically, inspired by large language models (LLMs), we propose a language embedding framework where both neural architectures and hardware platform specifications are projected into a unified semantic space through tokenization and LLM processing, enabling zero-shot prediction across different hardware platforms for the first time. Then, we propose a dynamic graph-based transformer for modeling neural architectures, resulting in improved neural architecture modeling performance. On the NNLQP benchmark, LeDG-Former surpasses previous methods, establishing a new SOTA while demonstrating the first successful cross-hardware latency prediction capability. Furthermore, our framework achieves superior performance on the cell-structured NAS-Bench-101 and NAS-Bench-201 datasets.

Shengqin Jiang, Linfei Li, Haokui Zhang et al.

As the number of individuals in a crowd grows, enumeration-based techniques become increasingly infeasible and their estimates increasingly unreliable. We propose instead an estimation-based version of the problem: we label Rough Crowd Counting that delivers better accuracy on the basis of training data that is easier to acquire. Rough crowd counting requires only rough annotations of the number of targets in an image, instead of the more traditional, and far more expensive, per-target annotations. We propose an approach to the rough crowd counting problem based on CLIP, termed ProgRoCC. Specifically, we introduce a progressive estimation learning strategy that determines the object count through a coarse-to-fine approach. This approach delivers answers quickly, outperforms the state-of-the-art in semi- and weakly-supervised crowd counting. In addition, we design a vision-language matching adapter that optimizes key-value pairs by mining effective matches of two modalities to refine the visual features, thereby improving the final performance. Extensive experimental results on three widely adopted crowd counting datasets demonstrate the effectiveness of our method.

Haokui Zhang, Buzhou Tang, Wenze Hu et al.

We propose a generic feature compression method for Approximate Nearest Neighbor Search (ANNS) problems, which speeds up existing ANNS methods in a plug-and-play manner. Specifically, based on transformer, we propose a new network structure to compress the feature into a low dimensional space, and an inhomogeneous neighborhood relationship preserving (INRP) loss that aims to maintain high search accuracy. Specifically, we use multiple compression projections to cast the feature into many low dimensional spaces, and then use transformer to globally optimize these projections such that the features are well compressed following the guidance from our loss function. The loss function is designed to assign high weights on point pairs that are close in original feature space, and keep their distances in projected space. Keeping these distances helps maintain the eventual top-k retrieval accuracy, and down weighting others creates room for feature compression. In experiments, we run our compression method on public datasets, and use the compressed features in graph based, product quantization and scalar quantization based ANNS solutions. Experimental results show that our compression method can significantly improve the efficiency of these methods while preserves or even improves search accuracy, suggesting its broad potential impact on real world applications.

Libo Sun, Haokui Zhang, Wei Yin

Road detection is a critically important task for self-driving cars. By employing LiDAR data, recent works have significantly improved the accuracy of road detection. Relying on LiDAR sensors limits the wide application of those methods when only cameras are available. In this paper, we propose a novel road detection approach with RGB being the only input during inference. Specifically, we exploit pseudo-LiDAR using depth estimation, and propose a feature fusion network where RGB and learned depth information are fused for improved road detection. To further optimize the network structure and improve the efficiency of the network. we search for the network structure of the feature fusion module using NAS techniques. Finally, be aware of that generating pseudo-LiDAR from RGB via depth estimation introduces extra computational costs and relies on depth estimation networks, we design a modality distillation strategy and leverage it to further free our network from these extra computational cost and dependencies during inference. The proposed method achieves state-of-the-art performance on two challenging benchmarks, KITTI and R2D.

Haokui Zhang, Chengrong Gong, Yunpeng Bai et al.

Hyperspectral images involve abundant spectral and spatial information, playing an irreplaceable role in land-cover classification. Recently, based on deep learning technologies, an increasing number of HSI classification approaches have been proposed, which demonstrate promising performance. However, previous studies suffer from two major drawbacks: 1) the architecture of most deep learning models is manually designed, relies on specialized knowledge, and is relatively tedious. Moreover, in HSI classifications, datasets captured by different sensors have different physical properties. Correspondingly, different models need to be designed for different datasets, which further increases the workload of designing architectures; 2) the mainstream framework is a patch-to-pixel framework. The overlap regions of patches of adjacent pixels are calculated repeatedly, which increases computational cost and time cost. Besides, the classification accuracy is sensitive to the patch size, which is artificially set based on extensive investigation experiments. To overcome the issues mentioned above, we firstly propose a 3D asymmetric neural network search algorithm and leverage it to automatically search for efficient architectures for HSI classifications. By analysing the characteristics of HSIs, we specifically build a 3D asymmetric decomposition search space, where spectral and spatial information are processed with different decomposition convolutions. Furthermore, we propose a new fast classification framework, i,e., pixel-to-pixel classification framework, which has no repetitive operations and reduces the overall cost. Experiments on three public HSI datasets captured by different sensors demonstrate the networks designed by our 3D-ANAS achieve competitive performance compared to several state-of-the-art methods, while having a much faster inference speed.

Haokui Zhang, Ying Li, Yenan Jiang et al.

Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, because of very limited available training samples and massive model parameters, DL methods may suffer from overfitting. In this paper, we propose an end-to-end 3-D lightweight convolutional neural network (CNN) (abbreviated as 3-D-LWNet) for limited samples-based HSI classification. Compared with conventional 3-D-CNN models, the proposed 3-D-LWNet has a deeper network structure, less parameters, and lower computation cost, resulting in better classification performance. To further alleviate the small sample problem, we also propose two transfer learning strategies: 1) cross-sensor strategy, in which we pretrain a 3-D model in the source HSI data sets containing a greater number of labeled samples and then transfer it to the target HSI data sets and 2) cross-modal strategy, in which we pretrain a 3-D model in the 2-D RGB image data sets containing a large number of samples and then transfer it to the target HSI data sets. In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets. Experiments on three public HSI data sets captured by different sensors demonstrate that our model achieves competitive performance for HSI classification compared to several state-of-the-art methods

Yenan Jiang, Ying Li, Shanrong Zou et al.

In recent years, deep convolutional neural networks (CNNs) have shown impressive ability to represent hyperspectral images (HSIs) and achieved encouraging results in HSI classification. However, the existing CNN-based models operate at the patch-level, in which pixel is separately classified into classes using a patch of images around it. This patch-level classification will lead to a large number of repeated calculations, and it is difficult to determine the appropriate patch size that is beneficial to classification accuracy. In addition, the conventional CNN models operate convolutions with local receptive fields, which cause failures in modeling contextual spatial information. To overcome the aforementioned limitations, we propose a novel end-to-end, pixels-to-pixels fully convolutional spatial propagation network (FCSPN) for HSI classification. Our FCSPN consists of a 3D fully convolution network (3D-FCN) and a convolutional spatial propagation network (CSPN). Specifically, the 3D-FCN is firstly introduced for reliable preliminary classification, in which a novel dual separable residual (DSR) unit is proposed to effectively capture spectral and spatial information simultaneously with fewer parameters. Moreover, the channel-wise attention mechanism is adapted in the 3D-FCN to grasp the most informative channels from redundant channel information. Finally, the CSPN is introduced to capture the spatial correlations of HSI via learning a local linear spatial propagation, which allows maintaining the HSI spatial consistency and further refining the classification results. Experimental results on three HSI benchmark datasets demonstrate that the proposed FCSPN achieves state-of-the-art performance on HSI classification.

Yinglong Wang, Haokui Zhang, Yu Liu et al.

In recent years, deep learning based methods have made significant progress in rain-removing. However, the existing methods usually do not have good generalization ability, which leads to the fact that almost all of existing methods have a satisfied performance on removing a specific type of rain streaks, but may have a relatively poor performance on other types of rain streaks. In this paper, aiming at removing multiple types of rain streaks from single images, we propose a novel deraining framework (GRASPP-GAN), which has better generalization capacity. Specifically, a modified ResNet-18 which extracts the deep features of rainy images and a revised ASPP structure which adapts to the various shapes and sizes of rain streaks are composed together to form the backbone of our deraining network. Taking the more prominent characteristics of rain streaks in the gradient domain into consideration, a gradient loss is introduced to help to supervise our deraining training process, for which, a Sobel convolution layer is built to extract the gradient information flexibly. To further boost the performance, an adversarial learning scheme is employed for the first time to train the proposed network. Extensive experiments on both real-world and synthetic datasets demonstrate that our method outperforms the state-of-the-art deraining methods quantitatively and qualitatively. In addition, without any modifications, our proposed framework also achieves good visual performance on dehazing.

Yu Liu, Lingqiao Liu, Haokui Zhang et al.

This paper tackles the problem of video object segmentation. We are specifically concerned with the task of segmenting all pixels of a target object in all frames, given the annotation mask in the first frame. Even when such annotation is available this remains a challenging problem because of the changing appearance and shape of the object over time. In this paper, we tackle this task by formulating it as a meta-learning problem, where the base learner grasping the semantic scene understanding for a general type of objects, and the meta learner quickly adapting the appearance of the target object with a few examples. Our proposed meta-learning method uses a closed form optimizer, the so-called "ridge regression", which has been shown to be conducive for fast and better training convergence. Moreover, we propose a mechanism, named "block splitting", to further speed up the training process as well as to reduce the number of learning parameters. In comparison with the-state-of-the art methods, our proposed framework achieves significant boost up in processing speed, while having very competitive performance compared to the best performing methods on the widely used datasets.

Haokui Zhang, Ying Li, Hao Chen et al.

Recently, neural architecture search (NAS) methods have attracted much attention and outperformed manually designed architectures on a few high-level vision tasks. In this paper, we propose HiNAS (Hierarchical NAS), an effort towards employing NAS to automatically design effective neural network architectures for image denoising. HiNAS adopts gradient based search strategies and employs operations with adaptive receptive field to build an flexible hierarchical search space. During the search stage, HiNAS shares cells across different feature levels to save memory and employ an early stopping strategy to avoid the collapse issue in NAS, and considerably accelerate the search speed. The proposed HiNAS is both memory and computation efficient, which takes only about 4.5 hours for searching using a single GPU. We evaluate the effectiveness of our proposed HiNAS on two different datasets, namely an additive white Gaussian noise dataset BSD500, and a realistic noise dataset SIM1800. Experimental results show that the architecture found by HiNAS has fewer parameters and enjoys a faster inference speed, while achieving highly competitive performance compared with state-of-the-art methods. We also present analysis on the architectures found by NAS. HiNAS also shows good performance on experiments for image de-raining.

Haokui Zhang, Ying Li, Peng Wang et al.

Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition. However, most of the existing action recognition models solely using RGB videos limit the performance capacity. Additionally, the state-of-the-art action recognition models, namely 3D convolutional neural networks (3D-CNNs) contain tremendous parameters suffering from computational inefficiency. In this paper, we propose a series of 3D light-weight architectures for action recognition based on RGB-D data. Compared with conventional 3D-CNN models, the proposed light-weight 3D-CNNs have considerably less parameters involving lower computation cost, while it results in favorable recognition performance. Experimental results on two public benchmark datasets show that our models can approximate or outperform the state-of-the-art approaches. Specifically, on the RGB+D-NTU (NTU) dataset, we achieve 93.2% and 97.6% for cross-subject and cross-view measurement, and on the Northwestern-UCLA Multiview Action 3D (N-UCLA) dataset, we achieve 95.5% accuracy of cross-view.