论文检索

Lintong Zhang, Kang Yin, Seong-Whan Lee

Attribution-based explanation techniques capture key patterns to enhance visual interpretability. However, these patterns often lack the granularity needed for insight in fine-grained tasks, particularly in cases of model misclassification, where explanations may be insufficiently detailed. To address this limitation, we propose a fine-grained counterfactual explanation framework that generates both object-level and part-level interpretability, addressing two fundamental questions: (1) which fine-grained features contribute to model misclassification, and (2) where dominant local features influence counterfactual adjustments. Our approach yields explainable counterfactuals in a non-generative manner by quantifying similarity and weighting component contributions within regions of interest between correctly classified and misclassified samples. Furthermore, we introduce an importance-isolation module grounded in Shapley value contributions, isolating features with region-specific relevance. Extensive experiments demonstrate the superiority of our approach in capturing more granular, intuitively meaningful regions, surpassing fine-grained methods.

Xuesong Chen, Linjiang Huang, Tao Ma, Rongyao Fang, Shaoshuai Shi, Hongsheng Li

The integration of Vision-Language Models (VLMs) into autonomous driving systems has shown promise in addressing key challenges such as learning complexity, interpretability, and common-sense reasoning. However, existing approaches often struggle with efficient integration and real-time decision-making due to computational demands. In this paper, we introduce SOLVE, an innovative framework that synergizes VLMs with end-to-end (E2E) models to enhance autonomous vehicle planning. Our approach emphasizes knowledge sharing at the feature level through a shared visual encoder, enabling comprehensive interaction between VLM and E2E components. We propose a Trajectory Chain-of-Thought (T-CoT) paradigm, which progressively refines trajectory predictions, reducing uncertainty and improving accuracy. By employing a temporal decoupling strategy, SOLVE achieves efficient asynchronous cooperation, aligning high-quality VLM outputs with E2E real-time performance. Evaluated on the nuScenes dataset, our method demonstrates significant improvements in trajectory prediction accuracy, paving the way for more robust and reliable autonomous driving systems.

Damiano Marsili, Rohun Agrawal, Yisong Yue, Georgia Gkioxari

Visual reasoning -- the ability to interpret the visual world -- is crucial for embodied agents that operate within three-dimensional scenes. Progress in AI has led to vision and language models capable of answering questions from images. However, their performance declines when tasked with 3D spatial reasoning. To tackle the complexity of such reasoning problems, we introduce an agentic program synthesis approach where LLM agents collaboratively generate a Pythonic API with new functions to solve common subproblems. Our method overcomes limitations of prior approaches that rely on a static, human-defined API, allowing it to handle a wider range of queries. To assess AI capabilities for 3D understanding, we introduce a new benchmark of queries involving multiple steps of grounding and inference. We show that our method outperforms prior zero-shot models for visual reasoning in 3D and empirically validate the effectiveness of our agentic framework for 3D spatial reasoning tasks. Project website: https://glab-caltech.github.io/vadar/

Yang Liu, Tianwei Zhang, Shi Gu

Concept Bottleneck Models (CBMs) provide an interpretable framework for neural networks by mapping visual features to predefined, human-understandable concepts. However, the application of CBMs is often constrained by insufficient concept annotations. Recently, multi-modal pre-trained models have shown promise in reducing annotation costs by aligning visual representations with textual concept embeddings. Nevertheless, the quality and completeness of the predefined concepts significantly affect the performance of CBMs.In this work, we propose Hybrid Concept Bottleneck Model (HybridCBM), a novel CBM framework to address the challenge of incomplete predefined concepts. Our method consists of two main components: a Static Concept Bank and a Dynamic Concept Bank. The Static Concept Bank directly leverages large language models (LLMs) for concept construction, while the Dynamic Concept Bank employs learnable vectors to capture complementary and valuable concepts continuously during training. After training, a pre-trained translator converts these vectors into human-understandable concepts, further enhancing model interpretability. Notably, HybridCBM is highly flexible and can be easily applied to any CBM to improve performance. Experimental results across multiple datasets demonstrate that HybridCBM outperforms current state-of-the-art methods and achieves comparable results to black-box models. Additionally, we propose novel metrics to evaluate the quality of the learned concepts, showing that they perform comparably to predefined concepts.

Ruoyu Chen, Siyuan Liang, Jingzhi Li, Shiming Liu, Maosen Li, Zhen Huang, Hua Zhang, Xiaochun Cao

Advances in multimodal pre-training have propelled object-level foundation models, such as Grounding DINO and Florence-2, in tasks like visual grounding and object detection. However, interpreting these models' decisions has grown increasingly challenging. Existing interpretable attribution methods for object-level task interpretation have notable limitations: (1) gradient-based methods lack precise localization due to visual-textual fusion in foundation models, and (2) perturbation-based methods produce noisy saliency maps, limiting fine-grained interpretability. To address these, we propose a Visual Precision Search method that generates accurate attribution maps with fewer regions. Our method bypasses internal model parameters to overcome attribution issues from multimodal fusion, dividing inputs into sparse sub-regions and using consistency and collaboration scores to accurately identify critical decision-making regions. We also conducted a theoretical analysis of the boundary guarantees and scope of applicability of our method. Experiments on RefCOCO, MS COCO, and LVIS show our approach enhances object-level task interpretability over SOTA for Grounding DINO and Florence-2 across various evaluation metrics, with faithfulness gains of 23.7%, 31.6%, and 20.1% on MS COCO, LVIS, and RefCOCO for Grounding DINO, and 50.7% and 66.9% on MS COCO and RefCOCO for Florence-2. Additionally, our method can interpret failures in visual grounding and object detection tasks, surpassing existing methods across multiple evaluation metrics. The code is released at https://github.com/RuoyuChen10/VPS.

Yusuf Dalva, Kavana Venkatesh, Pinar Yanardag

Rectified flow models have emerged as a dominant approach in image generation, showcasing impressive capabilities in high-quality image synthesis. However, despite their effectiveness in visual generation, rectified flow models often struggle with disentangled editing of images. This limitation prevents the ability to perform precise, attribute-specific modifications without affecting unrelated aspects of the image. In this paper, we introduce FluxSpace, a domain-agnostic image editing method leveraging a representation space with the ability to control the semantics of images generated by rectified flow transformers, such as Flux. By leveraging the representations learned by the transformer blocks within the rectified flow models, we propose a set of semantically interpretable representations that enable a wide range of image editing tasks, from fine-grained image editing to artistic creation. This work offers a scalable and effective image editing approach, along with its disentanglement capabilities.

Youngjoon Jang, Haran Raajesh, Liliane Momeni, Gül Varol, Andrew Zisserman

Our objective is to translate continuous sign language into spoken language text. Inspired by the way human interpreters rely on context for accurate translation, we incorporate additional contextual cues together with the signing video, into a new translation framework. Specifically, besides visual sign recognition features that encode the input video, we integrate complementary textual information from (i) captions describing the background show, (ii) translation of previous sentences, as well as (iii) pseudo-glosses transcribing the signing. These are automatically extracted and inputted along with the visual features to a pre-trained large language model (LLM), which we fine-tune to generate spoken language translations in text form. Through extensive ablation studies, we show the positive contribution of each input cue to the translation performance. We train and evaluate our approach on BOBSL -- the largest British Sign Language dataset currently available. We show that our contextual approach significantly enhances the quality of the translations compared to previously reported results on BOBSL, and also to state-of-the-art methods that we implement as baselines. Furthermore, we demonstrate the generality of our approach by applying it also to How2Sign, an American Sign Language dataset, and achieve competitive results.

Siyuan Liang, Jiawei Liang, Tianyu Pang, Chao Du, Aishan Liu, Mingli Zhu, Xiaochun Cao, Dacheng Tao

Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static settings, this paper explores backdoor attacks in LVLM instruction tuning across mismatched training and testing domains. We introduce a new evaluation dimension, backdoor domain generalization, to assess attack robustness under visual and text domain shifts. Our findings reveal two insights: (1) backdoor generalizability improves when distinctive trigger patterns are independent of specific data domains or model architectures, and (2) the competitive interaction between trigger patterns and clean semantic regions, where guiding the model to predict triggers enhances attack generalizability. Based on these insights, we propose a multimodal attribution backdoor attack (MABA) that injects domain-agnostic triggers into critical areas using attributional interpretation. Experiments with OpenFlamingo, Blip-2, and Otter show that MABA significantly boosts the attack success rate of generalization by 36.4% over the unimodal attack, achieving a 97% success rate at a 0.2% poisoning rate. This study reveals limitations in current evaluations and highlights how enhanced backdoor generalizability poses a security threat to LVLMs, even without test data access.

Yunlong Tang, Junjia Guo, Hang Hua, Susan Liang, Mingqian Feng, Xinyang Li, Rui Mao, Chao Huang, Jing Bi, Zeliang Zhang 等

The advancement of Multimodal Large Language Models (MLLMs) has enabled significant progress in multimodal understanding, expanding their capacity to analyze video content. However, existing evaluation benchmarks for MLLMs primarily focus on abstract video comprehension, lacking a detailed assessment of their ability to understand video compositions, the nuanced interpretation of how visual elements combine and interact within highly compiled video contexts. We introduce VidComposition, a new benchmark specifically designed to evaluate the video composition understanding capabilities of MLLMs using carefully curated compiled videos and cinematic-level annotations.VidComposition includes 982 videos with 1706 multiple-choice questions, covering various compositional aspects such as camera movement, angle, shot size, narrative structure, character actions and emotions, etc. Our comprehensive evaluation of 33 open-source and proprietary MLLMs reveals a significant performance gap between human and model capabilities. This highlights the limitations of current MLLMs in understanding complex, compiled video compositions and offers insights into areas for further improvement. Our benchmark is publicly available at https://yunlong10.github.io/VidComposition/

Arpita Chowdhury, Dipanjyoti Paul, Zheda Mai, Jianyang Gu, Ziheng Zhang, Kazi Sajeed Mehrab, Elizabeth G. Campolongo, Daniel Rubenstein, Charles V. Stewart, Anuj Karpatne 等

We present a simple approach to make pre-trained Vision Transformers (ViTs) interpretable for fine-grained analysis, aiming to identify and localize the traits that distinguish visually similar categories, such as bird species. Pre-trained ViTs, such as DINO, have demonstrated remarkable capabilities in extracting localized, discriminative features. However, saliency maps like Grad-CAM often fail to identify these traits, producing blurred, coarse heatmaps that highlight entire objects instead. We propose a novel approach, Prompt Class Attention Map (Prompt-CAM), to address this limitation. Prompt-CAM learns class-specific prompts for a pre-trained ViT and uses the corresponding outputs for classification. To correctly classify an image, the true-class prompt must attend to unique image patches not present in other classes' images (i.e., traits). As a result, the true class's multi-head attention maps reveal traits and their locations. Implementation-wise, Prompt-CAM is almost a "free lunch," requiring only a modification to the prediction head of Visual Prompt Tuning (VPT). This makes Prompt-CAM easy to train and apply, in stark contrast to other interpretable methods that require designing specific models and training processes. Extensive empirical studies on a dozen datasets from various domains (e.g., birds, fishes, insects, fungi, flowers, food, and cars) validate the superior interpretation capability of Prompt-CAM. The source code and demo are available at https://github.com/Imageomics/Prompt_CAM.

Vishesh Kumar, Akshay Agarwal

Deep Neural Networks (DNNs), backbone architecture in `almost' every computer vision task, are vulnerable to adversarial attacks, particularly physical out-of-distribution (OOD) adversarial patches. Existing defense models often struggle with interpreting these attacks in ways that align with human visual perception. Our proposed AdvPatchXAI approach introduces a generalized, robust, and explainable defense algorithm designed to defend DNNs against physical adversarial threats. AdvPatchXAI employs a novel patch decorrelation loss that reduces feature redundancy and enhances the distinctiveness of patch representations, enabling better generalization across unseen adversarial scenarios. It learns prototypical parts self-supervised, enhancing interpretability and correlation with human vision. The model utilizes a sparse linear layer for classification, making the decision process globally interpretable through a set of learned prototypes and locally explainable by pinpointing relevant prototypes within an image. Our comprehensive evaluation shows that AdvPatchXAI closes the "semantic" gap between latent space and pixel space and effectively handles unseen adversarial patches even perturbed with unseen corruptions, thereby significantly advancing DNN robustness in practical settings(https://github.com/tbvl22/Unified-resilient-and-Explainable-Adversarial-Patch-detector).

Erjian Guo, Zhen Zhao, Zicheng Wang, Tong Chen, Yunyi Liu, Luping Zhou

Medical Visual Question Answering (Med-VQA) systems benefit the interpretation of medical images containing critical clinical information. However, the challenge of noisy labels and limited high-quality datasets remains underexplored. To address this, we establish the first benchmark for noisy labels in Med-VQA by simulating human mislabeling with semantically designed noise types. More importantly, we introduce the DiN framework, which leverages a diffusion model to handle noisy labels in Med-VQA. Unlike the dominant classification-based VQA approaches that directly predict answers, our Answer Diffuser (AD) module employs a coarse-to-fine process, refining answer candidates with a diffusion model for improved accuracy. The Answer Condition Generator (ACG) further enhances this process by generating task-specific conditional information via integrating answer embeddings with fused image-question features. To address label noise, our Noisy Label Refinement(NLR) module introduces a robust loss function and dynamic answer adjustment to further boost the performance of the AD module. Our DiN framework consistently outperforms existing methods across multiple benchmarks with varying noise levels.

Pascal Chang, Sergio Sancho, Jingwei Tang, Markus Gross, Vinicius Azevedo

Anamorphosis refers to a category of images that are intentionally distorted, making them unrecognizable when viewed directly. Their true form only reveals itself when seen from a specific viewpoint, which can be through some catadioptric device like a mirror or a lens. While the construction of these mathematical devices can be traced back to as early as the 17th century, they are only interpretable when viewed from a specific vantage point and tend to lose meaning when seen normally. In this paper, we revisit these famous optical illusions with a generative twist. With the help of latent rectified flow models, we propose a method to create anamorphic images that still retain a valid interpretation when viewed directly. To this end, we introduce Laplacian Pyramid Warping, a frequency-aware image warping technique key to generating high-quality visuals. Our work extends Visual Anagrams (Geng et al. 2024) to latent space models and to a wider range of spatial transforms, enabling the creation of novel generative perceptual illusions.

Utkarsh Mall, Cheng Perng Phoo, Mia Chiquier, Bharath Hariharan, Kavita Bala, Carl Vondrick

Visual data is used in numerous different scientific workflows ranging from remote sensing to ecology. As the amount of observation data increases, the challenge is not just to make accurate predictions but also to understand the underlying mechanisms for those predictions. Good interpretation is important in scientific workflows, as it allows for better decision-making by providing insights into the data. This paper introduces an automatic way of obtaining such interpretable-by-design models, by learning programs that interleave neural networks. We propose DiSciPLE (Discovering Scientific Programs using LLMs and Evolution) an evolutionary algorithm that leverages common sense and prior knowledge of large language models (LLMs) to create Python programs explaining visual data. Additionally, we propose two improvements: a program critic and a program simplifier to improve our method further to synthesize good programs. On three different real world problems, DiSciPLE learns state-of-the-art programs on novel tasks with no prior literature. For example, we can learn programs with 35% lower error than the closest non-interpretable baseline for population density estimation.

Xuli Shen, Hua Cai, Weilin Shen, Qing Xu, Dingding Yu, Weifeng Ge, Xiangyang Xue

With the explosion of human-machine interaction, emotion recognition has reignited attention. Previous works focus on improving visual feature fusion and reasoning from multiple image levels. Although it is non-trivial to deduce a person's emotion by integrating multi-level feature (head, body and context), the emotion recognition results of each level is usually different from one another, which creates inconsistency in the prevailing feature alignment method and decrease recognition performance. In this work, we propose a multi-level image feature refinement method for emotion recognition (CocoER) to mitigate the impact caused by conflicting results from multi-level recognition. First, we leverage cross-level attention to improve visual feature consistency between hierarchically cropped head, body and context windows. Then, vocabulary informed alignment is incorporated into the recognition framework to produce pseudo label and guide hierarchical visual feature refinement. To effectively fuse multi-level feature, we elaborate on a competition process of eliminating irrelevant image level predictions and a coordination process to enhance the feature across all levels. Extensive experiments are executed on two popular datasets, and our method achieves state-of-the-art performance with multi-level interpretation results.

Ziqi Li, Tao Gao, Yisheng An, Ting Chen, Jing Zhang, Yuanbo Wen, Mengkun Liu, Qianxi Zhang

Brain-inspired spiking neural networks (SNNs) have the capability of energy-efficient processing of temporal information. However, leveraging the rich dynamic characteristics of SNNs and prior works in artificial neural networks (ANNs) to construct an effective object detection model for visual tasks remains an open question for further exploration. To develop a directly-trained , low energy consumption and high-performance multi-scale SNN model, we propose a novel interpretable object detection framework Multi-scale Spiking Detector (MSD). Initially, we propose a spiking convolutional neuron as a core component of the Optic Nerve Nucleus Block (ONNB), designed to significantly enhance the deep feature extraction capabilities of SNNs. ONNB enables direct training with improved energy efficiency, demonstrating superior performance compared to state-of-the-art ANN-to-SNN conversion and SNN techniques. In addition, we propose a Multi-scale Spiking Detection Framework to emulate the biological response and comprehension of stimuli from different objects. Wherein, spiking multi-scale fusion and the spiking detector are employed to integrate features across different depths and to detect response outcomes, respectively. Our method outperforms state-of-the-art ANN detectors, with only 7.8 M parameters and 6.43 mJ energy consumption. MSD obtains the mean average precision (mAP) of 62.0% and 66.3% on COCO and Gen1 datasets, respectively.

Zhijie Zhu, Lei Fan, Maurice Pagnucco, Yang Song

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to their ability to mimic human visual reasoning by providing explanations based on prototypical object parts. However, the quality of the explanations generated by these methods leaves room for improvement, as the prototypes usually focus on repetitive and redundant concepts. Leveraging recent advances in prototype learning, we present a framework for part-based interpretable image classification that learns a set of semantically distinctive object parts for each class, and provides diverse and comprehensive explanations. The core of our method is to learn the part-prototypes in a non-parametric fashion, through clustering deep features extracted from foundation vision models that encode robust semantic information. To quantitatively evaluate the quality of explanations provided by ProtoPNets, we introduce Distinctiveness Score and Comprehensiveness Score. Through evaluation on CUB-200-2011, Stanford Cars and Stanford Dogs datasets, we show that our framework compares favourably against existing ProtoPNets while achieving better interpretability.

Manishit Kundu, Sumit Shekhar, Pushpak Bhattacharyya

Visual metaphors are a complex vision–language phenomenon that requires both perceptual and conceptual reasoning to understand. They provide a valuable test of a model’s ability to interpret visual input and reason about it with creativity and coherence. We introduce ImageMet, a visual metaphor dataset, featuring 2177 synthetic and 350 human-annotated images. We benchmark several SOTA VLMs on two tasks: Visual Metaphor Captioning (VMC) and Visual Metaphor VQA (VM-VQA). We establish strong baselines by fine-tuning on ImageMet, which yields substantial performance gains in VMC (+4.67% SBERT-Similarity, +4.84% task-specific metric) and VM-VQA (+9.3% Accuracy on average). Additionally, we introduce a task-specific CoT prompting strategy that outperforms standard few-shot baselines (+1.99% in VMC, +5.21% in VM-VQA). We observe that despite strong performance on the VMC task, VLMs still significantly lag behind humans in understanding visual metaphors, indicating that their success often relies on learned associations rather than genuine analytical reasoning. We note that this gap is often obscured in metaphor captioning tasks where the automatic metrics correlate only moderately at best with human judgment (Pearson r < 0.6), highlighting the need for careful, holistic evaluation of the visual metaphor understanding of the models.

Wenyan Li, Raphael Tang, Chengzu Li, Caiqi Zhang, Ivan Vulić, Anders Søgaard

Vision–language models (VLMs) often process visual inputs through a pretrained vision encoder, followed by a projection into the language model’s embedding space via a connector component. While crucial for modality fusion, the potential information loss induced by this projection step and its direct impact on model capabilities remain understudied. We introduce two complementary approaches to examine and quantify this loss by analyzing the latent representation space. First, we evaluate semantic information preservation by analyzing changes in k-nearest neighbor relationships between image representations, before and after projection. Second, we directly measure information loss by reconstructing visual embeddings from the projected representation, localizing loss at an image patch level. Experiments reveal that connectors substantially distort the local geometry of visual representations, with k-nearest neighbors diverging by 40–60% post-projection, correlating with degradation in retrieval performance. The patch-level embedding reconstruction provides interpretable insights for model behavior on visually grounded question-answering tasks, finding that areas of high information loss reliably predict instances where models struggle.

Jiaqi Duan, Xiaoda Yang, Kaixuan Luan, Hongshun Qiu, Weicai Yan, Xueyi Zhang, Youliang Zhang, Zhaoyang Li, Donglin Huang, JunYu Lu 等

Object detection is a core challenge in computer vision. Traditional methods primarily rely on intermediate modalities such as text, speech, or visual cues to interpret user intent, leading to inefficient and potentially distorted expressions of intent. Brain signals, particularly fMRI signals, emerge as a novel modality that can directly reflect user intent, eliminating ambiguities introduced during modality conversion. However, brain signal-based object detection still faces challenges in accuracy and robustness. To address these challenges, we present BrainLoc, a lightweight object detection model guided by fMRI signals. First, we employ a multi-modal alignment strategy that enhances fMRI signal feature extraction by incorporating various modalities including images and text. Second, we propose a cross-domain fusion module that promotes interaction between fMRI features and category features, improving the representation of category information in fMRI signals. Extensive experiments demonstrate that BrainLoc achieves state-of-the-art performance in brain signal-based object detection tasks, showing significant advantages in both accuracy and convenience.