论文检索

Xiang Yin, Nico Potyka, Francesca Toni

Quantitatively explaining the strength of arguments under gradual semantics has recently received increasing attention. Specifically, several works in the literature provide quantitative explanations by computing the attribution scores of arguments. These works disregard the importance of attacks and supports, even though they play an essential role when explaining arguments' strength. In this paper, we propose a novel theory of Relation Attribution Explanations (RAEs), adapting Shapley values from game theory to offer fine-grained insights into the role of attacks and supports in quantitative bipolar argumentation towards obtaining the arguments' strength. We show that RAEs satisfy several desirable properties. We also propose a probabilistic algorithm to approximate RAEs efficiently. Finally, we show the application value of RAEs in fraud detection and large language models case studies.

Nathaniel Weir, Peter Clark, Benjamin Van Durme

Our goal is to develop a modern approach to answering questions via systematic reasoning where answers are supported by human interpretable proof trees grounded in an NL corpus of facts. Such a system would help alleviate the challenges of interpretability and hallucination with modern LMs, and the lack of grounding of current explanation methods (e.g., Chain-of-Thought). This paper proposes a new take on Prolog-based inference engines, where we replace handcrafted rules with a combination of neural language modeling, guided generation, and semiparametric dense retrieval. Our implementation, NELLIE, is the first system to demonstrate fully interpretable, end-to-end grounded QA as entailment tree proof search, going beyond earlier work explaining known-to-be-true facts from text. In experiments, NELLIE outperforms a similar-sized state-of-the-art reasoner while producing knowledge-grounded explanations. We also find NELLIE can exploit both semi-structured and NL text corpora to guide reasoning. Together these suggest a new way to jointly reap the benefits of both modern neural methods and traditional symbolic reasoning.

Tiago de Lima, Emiliano Lorini

We present a novel modal language for causal reasoning and interpret it by means of a semantics in which causal information is represented using causal bases in propositional form. The language includes modal operators of conditional causal necessity where the condition is a causal change operation. We provide a succinct formulation of model checking for our language and a model checking procedure based on a polysize reduction to QBF. We illustrate the expressiveness of our language through some examples and show that it allows us to represent and to formally verify a variety of concepts studied in the field of explainable AI including abductive explanation, intervention and actual cause.

Chen Wei, Jiachen Zou, Dietmar Heinke, Quanying Liu

A central question for cognitive science is to understand how humans process visual scenes, i.e, to uncover human low-dimensional concept representation space from high-dimensional visual stimuli. Generating visual stimuli with controlling concepts is the key. However, there are currently no generative models in AI to solve this problem. Here, we present the Concept based Controllable Generation (CoCoG) framework. CoCoG consists of two components, a simple yet efficient AI agent for extracting interpretable concept and predicting human decision-making in visual similarity judgment tasks, and a conditional generation model for generating visual stimuli given the concepts. We quantify the performance of CoCoG from two aspects, the human behavior prediction accuracy and the controllable generation ability. The experiments with CoCoG indicate that 1) the reliable concept embeddings in CoCoG allows to predict human behavior with 64.07% accuracy in the THINGS-similarity dataset; 2) CoCoG can generate diverse stimuli through the control of concepts; 3) CoCoG can manipulate human similarity judgment behavior by intervening key concepts. CoCoG offers visual objects with controlling concepts to advance our understanding of causality in human cognition. The code of CoCoG framework is available at https://github.com/ncclab-sustech/CoCoG.

Yang Wang, Haiyang Mei, Qirui Bao, Ziqi Wei, Mike Zheng Shou, Haizhou Li, Bo Dong, Xin Yang

We introduce a novel multimodality synergistic knowledge distillation scheme tailored for efficient single-eye motion recognition tasks. This method allows a lightweight, unimodal student spiking neural network (SNN) to extract rich knowledge from an event-frame multimodal teacher network. The core strength of this approach is its ability to utilize the ample, coarser temporal cues found in conventional frames for effective emotion recognition. Consequently, our method adeptly interprets both temporal and spatial information from the conventional frame domain, eliminating the need for specialized sensing devices, e.g., event-based camera. The effectiveness of our approach is thoroughly demonstrated using both existing and our compiled single-eye emotion recognition datasets, achieving unparalleled performance in accuracy and efficiency over existing state-of-the-art methods.

Jinduo Liu, Feipeng Wang, Junzhong Ji

Using deep models to classify brain functional networks (BFNs) for the auxiliary diagnosis and treatment of brain diseases has become increasingly popular. However, the unexplainability of deep models has seriously hindered their applications in computer-aided diagnosis. In addition, current explanation methods mostly focus on natural images, which cannot be directly used to explain the deep model for BFN classification. In this paper, we propose a concept-level causal explanation method for BFN classification called CLCEM. First, CLCEM employs the causal learning method to extract concepts that are meaningful to humans from BFNs. Second, it aggregates the same concepts to obtain the contribution of each concept to the model output. Finally, CLCEM adds the contribution of each concept to make a diagnosis. The experimental results show that our CLCEM can not only accurately identify brain regions related to specific brain diseases but also make decisions based on the concepts of these brain regions, which enables humans to understand the decision-making process without performance degradation.

Di Wu, Shicai Fan, Xue Zhou, Li Yu, Yuzhong Deng, Jianxiao Zou, Baihong Lin

Reconstruction-based methods have been commonly used for unsupervised anomaly detection, in which a normal image is reconstructed and compared with the given test image to detect and locate anomalies. Recently, diffusion models have shown promising applications for anomaly detection due to their powerful generative ability. However, these models lack strict mathematical support for normal image reconstruction and unexpectedly suffer from low reconstruction quality. To address these issues, this paper proposes a novel and highly-interpretable method named Masked Diffusion Posterior Sampling (MDPS). In MDPS, the problem of normal image reconstruction is mathematically modeled as multiple diffusion posterior sampling for normal images based on the devised masked noisy observation model and the diffusion-based normal image prior under Bayesian framework. Using a metric designed from pixel-level and perceptual-level perspectives, MDPS can effectively compute the difference map between each normal posterior sample and the given test image. Anomaly scores are obtained by averaging all difference maps for multiple posterior samples. Exhaustive experiments on MVTec and BTAD datasets demonstrate that MDPS can achieve state-of-the-art performance in normal image reconstruction quality as well as anomaly detection and localization.

Huiying Ma, Dongxiao He, Xiaobao Wang, Di Jin, Meng Ge, Longbiao Wang

With the advancement of the internet, sarcastic sentiment expression on social media has grown increasingly diverse. Consequently, multimodal sarcasm detection has emerged as a valuable tool for users to comprehend and interpret sarcastic expressions. Previous research suggests that effectively integrating three modalities (namely image, text, and their inconsistencies) enhances sarcasm detection. However, in some instances, sarcasm detection can be achieved using a single modality, while others necessitate multiple modalities for accurate recognition. This variability suggests that each modality contributes differently to sarcasm detection, and employing a traditional fusion method may introduce bias in the information, unable to explicitly demonstrate the prediction ability of each modality. Therefore, we propose a multimodal sarcasm detection method based on dual generative processes. The dual generative processes map features into the same semantic space to deeply explore emotional inconsistencies between modalities. Concurrently, by incorporating the concept of strong and weak modalities, we explicitly model the modalities' contributions based on prediction performance and autonomously adjust the weight distribution. Experimental results on publicly available multi-modal sarcasm detection datasets validate the superiority of our proposed model.

Kang Luo, Yuanshao Zhu, Wei Chen, Kun Wang, Zhengyang Zhou, Sijie Ruan, Yuxuan Liang

Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial context, leading to the acquisition of spurious correlations and limited generalization capabilities. To bridge this gap, we initially formulate a Structural Causal Model (SCM) to decipher the trajectory representation learning process from a causal perspective. Building upon the SCM, we further present a Trajectory modeling framework (TrajCL) based on Causal Learning, which leverages the backdoor adjustment theory as an intervention tool to eliminate the spurious correlations between geospatial context and trajectories. Extensive experiments on two real-world datasets verify that TrajCL markedly enhances performance in trajectory classification tasks while showcasing superior generalization and interpretability.

Zehua Liu, Jingyuan Wang, Zimeng Li, Yue He

Due to the complex and dynamic traffic contexts, the interpretability and uncertainty of traffic forecasting have gained increasing attention. Significance testing is a powerful tool in statistics used to determine whether a hypothesis is valid, facilitating the identification of pivotal features that predominantly contribute to the true relationship. However, existing works mainly regard traffic forecasting as a deterministic problem, making it challenging to perform effective significance testing. To fill this gap, we propose to conduct Full Bayesian Significance Testing for Neural Networks in Traffic Forecasting, namely ST-nFBST. A Bayesian neural network is utilized to capture the complicated traffic relationships through an optimization function resolved in the context of aleatoric uncertainty and epistemic uncertainty. Thereupon, ST-nFBST can achieve the significance testing by means of a delicate grad-based evidence value, further capturing the inherent traffic schema for better spatiotemporal modeling. Extensive experiments are conducted on METR-LA and PEMS-BAY to verify the advantages of our method in terms of uncertainty analysis and significance testing, helping the interpretability and promotion of traffic forecasting.

Jue Li, Yuhua Qian, Jieting Wang, Saixiong Liu

The Hilbert-Schmidt Independence Criterion (HSIC) based on kernel functions is capable of detecting nonlinear dependencies between variables, making it a common method for association relationship mining. However, in situations with small samples, high dimensions, or noisy data, it may generate spurious associations, causing two unrelated variables to have certain scores. To address this issue, we propose a novel criterion, named as Pure Hilbert-Schmidt Independence Criterion (PHSIC). PHSIC is achieved by subtracting the mean HSIC obtained under random conditions from the original HSIC value. We demonstrate three significant advantages of PHSIC through theoretical and simulation experiments: (1) PHSIC has a baseline of zero, enhancing the interpretability of HSIC. (2) Compared to HSIC, PHSIC exhibits lower bias. (3) PHSIC enables a fairer comparison across different samples and dimensions. To validate the effectiveness of PHSIC, we apply it to multiple causal inference tasks to measure the independence between cause and residual. Experimental results demonstrate that the causal model based on PHSIC performs well compared to other methods in scenarios involving small sample sizes and noisy data, both in real and simulated datasets.

Younes Mechqrane, Christian Bessiere, Ismail Elabbassi

Most active constraint acquisition systems suffer from two weaknesses. They require the explicit generation of the set of potential constraints (the bias), whose size can be prohibitive for practical use of these systems, and the answers to queries contain little information. In this paper, we introduce ACQNOGOODS, an active learning schema that does not require the construction of a bias. We then propose LLMACQ, an active learning system that incorporates a Large Language Model component in the ACQNOGOODS schema. LLMACQ interprets the user’s answers given in natural language, leading to more informative communication. As our experiments show, the non requirement of a bias in extension combined to the higher level communication with the user allow LLMACQ to learn constraints of any arity and to dramatically decrease the number of queries.

Kanglei Zhou, Junlin Li, Ruizhi Cai, Liyuan Wang, Xingxing Zhang, Xiaohui Liang

Action Quality Assessment (AQA) is pivotal for quantifying actions across domains like sports and medical care. Existing methods often rely on pre-trained backbones from large-scale action recognition datasets to boost performance on smaller AQA datasets. However, this common strategy yields suboptimal results due to the inherent struggle of these backbones to capture the subtle cues essential for AQA. Moreover, fine-tuning on smaller datasets risks overfitting. To address these issues, we propose Coarse-to-Fine Instruction Alignment (CoFInAl). Inspired by recent advances in large language model tuning, CoFInAl aligns AQA with broader pre-trained tasks by reformulating it as a coarse-to-fine classification task. Initially, it learns grade prototypes for coarse assessment and then utilizes fixed sub-grade prototypes for fine-grained assessment. This hierarchical approach mirrors the judging process, enhancing interpretability within the AQA framework. Experimental results on two long-term AQA datasets demonstrate CoFInAl achieves state-of-the-art performance with significant correlation gains of 5.49% and 3.55% on Rhythmic Gymnastics and Fis-V, respectively. Our Code is available at https://github.com/ZhouKanglei/CoFInAl_AQA.

Liangqi Zhang, Yihao Luo, Haibo Shen, Tianjiang Wang

Adversarial robustness and interpretability are longstanding challenges of computer vision. Deep neural networks are vulnerable to adversarial perturbations that are incomprehensible and imperceptible to humans. However, the opaqueness of networks prevents one from theoretically addressing adversarial robustness. As a human-comprehensible approach, the frequency perspective has been adopted in recent works to investigate the properties of neural networks and adversarial examples. In this paper, we investigate the frequency properties of feature extraction and analyze the stability of different frequency features when attacking different frequencies. Therefore, we propose an attack method, F-PGD, based on the projected gradient descent to attack the specified frequency bands. Utilizing this method, we find many intriguing properties of neural networks and adversarial perturbations. We experimentally show that contrary to the low-frequency bias of neural networks, the effective features of the same class are distributed across all frequency bands. Meanwhile, the high-frequency features often dominate when the neural networks make conflicting decisions on different frequency features. Furthermore, the attack experiments show that the low-frequency features are more robust to the attacks on different frequencies, but the interference to the high frequencies makes the network unable to make the right decision. These properties indicate that the decision-making process of neural networks tends to use as few low-frequency features as possible and cannot integrate features of different frequencies.

Mengqi Xue, Qihan Huang, Haofei Zhang, Jingwen Hu, Jie Song, Mingli Song, Canghong Jin

Prototypical part network (ProtoPNet) and its variants have drawn wide attention and been applied to various tasks due to their inherent self-explanatory property. Previous ProtoPNets are primarily built upon convolutional neural networks (CNNs). Therefore, it is natural to investigate whether these explainable methods can be advantageous for the recently emerged Vision Transformers (ViTs). However, directly utilizing ViT-backed models as backbones can lead to prototypes paying excessive attention to background positions rather than foreground objects (i.e., the “distraction” problem). To address the problem, this paper proposes prototypical part Transformer (ProtoPFormer) for interpretable image recognition. Based the architectural characteristics of ViTs, we modify the original ProtoPNet by creating separate global and local branches, each accompanied by corresponding prototypes that can capture and highlight representative holistic and partial features. Specifically, the global prototypes can guide local prototypes to concentrate on the foreground and effectively suppress the background influence. Subsequently, local prototypes are explicitly supervised to concentrate on different discriminative visual parts. Finally, the two branches mutually correct each other and jointly make the final decisions. Moreover, extensive experiments demonstrate that ProtoPFormer can consistently achieve superior performance on accuracy, visualization results, and quantitative interpretability evaluation over the state-of-the-art (SOTA) baselines. Our code has been released at https://github.com/zju-vipa/ProtoPFormer.

Likai Tian, Zhengwei Yang, Zechao Hu, Hao Li, Yifang Yin, Zheng Wang

The rise of online shopping and social media has spurred the Video-to-Shop Retrieval (VSR) task, which involves identifying fashion items (e.g., clothing) in videos and matching them with identical products provided by stores. In real-world scenarios, human movement in dynamic video scenes can cause substantial morphological alterations of fashion items with aspects of occlusion, shifting viewpoints (parallax), and partial visibility (truncation). This results in those high-quality frames being overwhelmed by a vast of redundant ones, which makes the retrieval less effectiveness. To this end, this paper introduces a framework, named Self-supervised Fashion-aware CLIP (SF-CLIP), for effective VSR. The SF-CLIP enables the discovery of salient frames with high fashion expressiveness via generating pseudo-labels from three key aspects of fashion expressiveness to assess occlusion, parallax, and truncation. With such pseudo-labels, the ability of CLIP is expanded to facilitate the discovery of salient frames. Furthermore, to encompass the comprehensive representations among salient frames, a dual-branch graph-based fusion module is proposed to extract and integrate inter-frame features. Extensive experiments demonstrate the superiority of SF-CLIP over the state-of-the-arts.

Hao Su, Meng Yang

Weakly Supervised Object Localization (WSOL) is a challenging task, which aims to learn object localization with less costly image-level labels. Existing convolution neural network (CNN) based methods tend to focus on discriminative regions of objects, while transformer-based methods overemphasize deep global features powerful for classification and lack the capability to perceive object details, leading to prediction results far from the object boundary. In this paper, we propose a novel Consistency and Integration Model with Adaptive Thresholds (CIAT) that exploits the spatial-semantic consistency between shallow and deep features to activate more object regions and detects the object regions adaptively in different images. First, we introduce a simple plug-and-play consistency and integration module of shallow-deep features (CISD), which utilizes shallow features efficiently to enhance the entire object perception. Then, we design an online adaptive threshold (OAT) based on Bayesian decision theory, which computes a reasonable segmentation threshold adaptive for the localization map of each image, making the predicted bounding box closer to the ground truth. Extensive experiments on two widely used CUB-200-2011 and ILSVRC datasets verify the effectiveness of our methods.

Yaohua Liu, Jiaxin Gao, Xuan Liu, Xianghao Jiao, Xin Fan, Risheng Liu

Transfer attacks generate significant interest for real-world black-box applications by crafting transferable adversarial examples through surrogate models. Whereas, existing works essentially directly optimize the single-level objective w.r.t. the surrogate model, which always leads to poor interpretability of attack mechanism and limited generalization performance over unknown victim models. In this work, we propose the BilEvel Transfer AttacK (BETAK) framework by establishing an initialization derived bilevel optimization paradigm, which explicitly reformulates the nested constraint relationship between the Upper-Level (UL) pseudo-victim attacker and the Lower-Level (LL) surrogate attacker. Algorithmically, we introduce the Hyper Gradient Response (HGR) estimation as an effective feedback for the transferability over pseudo-victim attackers, and propose the Dynamic Sequence Truncation (DST) technique to dynamically adjust the back-propagation path for HGR and reduce computational overhead simultaneously. Meanwhile, we conduct detailed algorithmic analysis and provide convergence guarantee to support non-convexity of the LL surrogate attacker. Extensive evaluations demonstrate substantial improvement of BETAK (e.g., 53.41% increase of attack success rates against IncRes-v2_ens victim) against different victims and defense methods in targeted and untargeted attack scenarios.

Wentao Jiang, Jing Zhang, Di Wang, Qiming Zhang, Zengmao Wang, Bo Du

Due to spatial redundancy in remote sensing images, sparse tokens containing rich information are usually involved in self-attention (SA) to reduce the overall token numbers within the calculation, avoiding the high computational cost issue in Vision Transformers. However, such methods usually obtain sparse tokens by hand-crafted or parallel-unfriendly designs, posing a challenge to reach a better balance between efficiency and performance. Different from them, this paper proposes to use learnable meta tokens to formulate sparse tokens, which effectively learn key information meanwhile improving the inference speed. Technically, the meta tokens are first initialized from image tokens via cross-attention. Then, we propose Dual Cross-Attention (DCA) to promote information exchange between image tokens and meta tokens, where they serve as query and key (value) tokens alternatively in a dual-branch structure, significantly reducing the computational complexity compared to self-attention. By employing DCA in the early stages with dense visual tokens, we obtain the hierarchical architecture LeMeViT with various sizes. Experimental results in classification and dense prediction tasks show that LeMeViT has a significant 1.7 × speedup, fewer parameters, and competitive performance compared to the baseline models, and achieves a better trade-off between efficiency and performance. The code is released at https://github.com/ViTAE-Transformer/LeMeViT.

Tao Dai, Jianping Wang, Hang Guo, Jinmin Li, Jinbao Wang, Zexuan Zhu

Transformer-based models have been widely and successfully used in various low-vision visual tasks, and have achieved remarkable performance in single image super-resolution (SR). Despite the significant progress in SR, Transformer-based SR methods (e.g., SwinIR) still suffer from the problems of heavy computation cost and low-frequency preference, while ignoring the reconstruction of rich high-frequency information, hence hindering the representational power of Transformers. To address these issues, in this paper, we propose a novel Frequency-aware Transformer (FreqFormer) for lightweight image SR. Specifically, a Frequency Division Module (FDM) is first introduced to separately handle high- and low-frequency information in a divide-and-conquer manner. Moreover, we present Frequency-aware Transformer Block (FTB) to extracting both spatial frequency attention and channel transposed attention to recover high-frequency details. Extensive experimental results on public datasets demonstrate the superiority of our FreqFormer over state-of-the-art SR methods in terms of both quantitative metrics and visual quality. Code and models are available at https://github.com/JPWang-CS/FreqFormer.