arXiv subjects

Haokui Zhang

Publications and source records attributed to Haokui Zhang.

At least 19 recordsLinked to original sources

arXiv2026

EGM-Det: Entropy-Guided Multimodal Adaptive Fusion for UAV RGB-IR Object Detection

Joint use of RGB and infrared (IR) imagery can improve UAV-view object detection, but most existing methods fuse multimodal features with static or fixed weights and therefore overlook spatially varying modality reliability. We propose EGM-Det, an entropy-guided multimodal adaptive fusion framework for RGB-IR object detection. EGM-Det employs a dual-stream architecture to preserve modality-specific representations and introduces an Entropy Offset Gate Fusion module for adaptive multi-scale fusion. The module derives shallow entropy priors from input intensity, local entropy, and cross-modal discrepancy, and uses them to guide local offset alignment and spatial-channel gated fusion. It therefore selectively aggregates reliable RGB and infrared cues instead of uniformly combining heterogeneous features. We further introduce cross-modal distillation to regularize the learned fusion gates and reduce fusion degradation. Each student branch extracts complementary knowledge from the cross-modality teacher branch matched to the main branch, while entropy-adaptive supervision emphasizes uncertain modality decisions. Experiments on DroneVehicle, LLVIP, and VEDAI demonstrate state-of-the-art performance across all three benchmarks; in particular, EGM-Det outperforms prior approaches by more than 10 percentage points on VEDAI.

cs.CV↗

arXiv2026

When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs

Abundant visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs. Existing visual token pruning methods rely on similarity-based guidance, which exploits pairwise text-vision and vision-vision token correlations for compression. However, such methods only capture local layer-level signals and overlook the whole inference process in VLM. In this paper, we revisit VLM inference and present a new efficient guidance scheme that complements similarity-based guidance. In particular, we identify a key observation: as LLM layers deepen, text tokens continuously aggregate visual information via self-attention and progressively absorb partial visual content into textual representations. To quantify this phenomenon, we propose Cross Modal Absorption (CMA) from a geometric representation perspective to measure how much visual information is absorbed by text, revealing that more visual tokens in deeper layers can be approximately explained by the text subspace. We accordingly propose Cross Modal Residual (CMR). It projects visual tokens onto the text subspace via Tikhonov regularized least squares and exploits reconstruction residuals to quantify visual information that cannot be explained by text. Finally, based on CMR, we present SIEVE, a training-free visual token compression method that combines CMR, text-attention relevance, and residual-space diversity to retain task-relevant and complementary tokens. Experiments on diverse VLM architectures verify the effectiveness of SIEVE. For instance, on LLaVA-NeXT-7B, SIEVE keeps only $11.1\%$ of visual tokens while preserving $97.5\%$ of the original average performance, achieving $3.62\times$ prefill speedup, $2.49\times$ end-to-end speedup, and a $6.02\times$ KV-cache reduction.

cs.CV↗

arXiv2026

DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration

All-in-One image restoration aims to develop a unified restoration framework for handling diverse degradation types. Existing end-to-end methods usually regard the restoration process as a black-box mapping, lacking an explicit optimization interpretation. Although deep unfolding provides an interpretable iterative modeling paradigm for image restoration, existing methods mostly rely on fixed degradation assumptions or predefined degradation information, making them difficult to adapt to unified restoration requirements under complex degradations and locally damaged content. This limitation restricts their performance in degradation suppression and structural detail recovery. To address these issues, this paper proposes DVANet, a deep unfolding network inspired by the half-quadratic splitting optimization algorithm, which formulates unified image restoration under complex degradations as a collaborative unfolding process between degradation-aware observation consistency and visual-prior-guided reconstruction. Specifically, in the degradation-aware observation consistency branch, a degradation representation module is employed to extract global degradation attributes and local degradation cues, and degradation-conditioned mapping is used to enhance the model's adaptability to different degradation types. In the visual-prior-guided reconstruction branch, DINOv3 is introduced to provide structural and semantic information as hierarchical visual priors, thereby complementing the missing structural information in damaged regions and improving detail recovery. Extensive experiments demonstrate that DVANet achieves superior or competitive performance on multi-scenario degradation and cross-domain image restoration tasks, showing favorable degradation adaptability and generalization ability.

cs.CV↗

arXiv2026

CC-Pan: Channel-wise Compression based Diffusion for Efficient Pan-Sharpening

Recently, diffusion models have brought novel insights to pan-sharpening and notably boosted fusion precision. However, most existing models perform diffusion in the pixel space and train distinct models for different multispectral (MS) sensors, suffering from high inference latency and sensor-specific limitations. In this paper, we present CC-Pan, a cross-sensor latent diffusion framework for efficient pan-sharpening. Specifically, CC-Pan trains a band-wise single-channel variational autoencoder (VAE) to encode high-resolution multispectral (HRMS) images into compact latent representations, naturally supporting MS images with varying band counts across different sensors and establishing a basis for inference acceleration. Spectral physical properties, along with PAN and MS images, are then injected into the diffusion backbone through carefully designed unidirectional and bidirectional interactive control structures, achieving high-precision spatial--spectral fusion in the latent diffusion process. Furthermore, a lightweight region-based cross-band attention (RCBA) module is incorporated at the central layer of the diffusion model, reinforcing inter-band spectral connections to boost spectral consistency and further elevate fusion precision. Extensive experimental results on GaoFen-2, QuickBird, and WorldView-3 demonstrate that CC-Pan outperforms state-of-the-art diffusion-based methods across all three benchmarks, attains a $2$--$3\times$ inference speedup, and exhibits robust cross-sensor generalization capability on the held-out WorldView-2 sensor without any sensor-specific retraining.

cs.CV↗

arXiv2026

TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language Models

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 TRIO 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. Specifically, 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 TRIO 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, TRIO retains just 11.1\% of visual tokens but maintains 97.2\% of the original performance, with a 2.75$\times$ prefill speedup, 2.14$\times$ inference speedup, 6.22$\times$ lower FLOPs, and 6.05$\times$ reduced KV Cache overhead.Our code is available at https://github.com/ocy1/TRIO.

cs.CV↗

arXiv2026

Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual Learning

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.

cs.CV↗

arXiv2026

M$^2$: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on extensive data collection and model training, yet still struggle with high computational costs and insufficient reasoning capabilities when facing complex, long-horizon scenarios. To address this, we propose M$^2$, a training-free, memory-augmented framework designed to optimize context efficiency and decision-making robustness. Our approach incorporates a dual-tier memory mechanism that synergizes Dynamic Trajectory Summarization (Internal Memory) to compress verbose interaction history into concise state updates, and Insight Retrieval Augmentation (External Memory) to guide the agent with actionable guidelines retrieved from an offline insight bank. Extensive evaluations across WebVoyager and OnlineMind2Web demonstrate that M$^2$ consistently surpasses baselines, yielding up to a 19.6% success rate increase and 58.7% token reduction for Qwen3-VL-32B, while proprietary models like Claude achieve accuracy gains up to 12.5% alongside significantly lower computational overhead.

cs.CV↗

arXiv2026

Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection

Open-Vocabulary Aerial Detection (OVAD) and Remote Sensing Visual Grounding (RSVG) have emerged as two key paradigms for aerial scene understanding. However, each paradigm suffers from inherent limitations when operating in isolation: OVAD is restricted to coarse category-level semantics, while RSVG is structurally limited to single-target localization. These limitations prevent existing methods from simultaneously supporting rich semantic understanding and multi-target detection. To address this, we propose OTA-Det, the first unified framework that bridges both paradigms into a cohesive architecture. Specifically, we introduce a task reformulation strategy that unifies task objectives and supervision mechanisms, enabling joint training across datasets from both paradigms with dense supervision signals. Furthermore, we propose a dense semantic alignment strategy that establishes explicit correspondence at multiple granularities, from holistic expressions to individual attributes, enabling fine-grained semantic understanding. To ensure real-time efficiency, OTA-Det builds upon the RT-DETR architecture, extending it from closed-set detection to open-text detection by introducing several high efficient modules, achieving state-of-the-art performance on six benchmarks spanning both OVAD and RSVG tasks while maintaining real-time inference at 34 FPS.

cs.CV↗

arXiv2026

Rethinking Practical and Efficient Quantization Calibration for Vision-Language Models

Post-training quantization (PTQ) is a primary approach for deploying large language models without fine-tuning, and the quantized performance is often strongly affected by the calibration in PTQ. By contrast, in vision-language models (VLMs), substantial differences between visual and text tokens in their activation distributions and sensitivities to quantization error pose significant challenges for effective calibration during PTQ. In this work, we rethink what PTQ calibration should align with in VLMs and propose the Token-level Importance-aware Layer-wise Quantization framework (TLQ). Guided by gradient information, we design a token-level importance integration mechanism for quantization error, and use it to construct a token-level calibration set, enabling a more fine-grained calibration strategy. Furthermore, TLQ introduces a multi-GPU, quantization-exposed layer-wise calibration scheme. This scheme keeps the layer-wise calibration procedure consistent with the true quantized inference path and distributes the complex layer-wise calibration workload across multiple RTX3090 GPUs, thereby reducing reliance on the large memory of A100 GPUs. TLQ is evaluated across two models, three model scales, and two quantization settings, consistently achieving performance improvements across all settings, indicating its strong quantization stability. The code will be released publicly.

cs.CV↗

arXiv2026

Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning

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.

cs.CV↗

arXiv2025

UVLM: Benchmarking Video Language Model for Underwater World Understanding

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.

cs.CV↗

arXiv2025

Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation

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.

cs.CV↗

arXiv2025

OS-W2S: An Automatic Labeling Engine for Language-Guided Open-Set Aerial Object Detection

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.

cs.CV↗

arXiv2025

Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy

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.

cs.CV↗

arXiv2025

Text-Visual Semantic Constrained AI-Generated Image Quality Assessment

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.

cs.CV↗

arXiv2025

RT-OVAD: Real-Time Open-Vocabulary Aerial Object Detection via Image-Text Collaboration

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.

cs.CV↗

arXiv2025

Open-Vocabulary Object Detection in UAV Imagery: A Review and Future Perspectives

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

cs.CV↗

arXiv2025

NN-Former: Rethinking Graph Structure in Neural Architecture Representation

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.

cs.LG↗