While Transformers have rapidly gained popularity in various computer vision applications, post-hoc explanations of their internal mechanisms remain largely unexplored. Vision Transformers extract visual information by representing image regions as transformed tokens and integrating them via attention weights. However, existing post-hoc explanation methods merely consider these attention weights, neglecting crucial information from the transformed tokens, which fails to accurately illustrate the rationales behind the models' predictions. To incorporate the influence of token transformation into interpretation, we propose TokenTM, a novel post-hoc explanation method that utilizes our introduced measurement of token transformation effects. Specifically, we quantify token transformation effects by measuring changes in token lengths and correlations in their directions pre- and post-transformation. Moreover, we develop initialization and aggregation rules to integrate both attention weights and token transformation effects across all layers, capturing holistic token contributions throughout the model. Experimental results on segmentation and perturbation tests demonstrate the superiority of our proposed TokenTM compared to state-of-the-art Vision Transformer explanation methods.
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be faithful to classifier predictions, which poses a significant challenge when attempting to debug models based on such explanations. To this end, we seek a methodology that can improve the faithfulness of an explanation method with respect to model predictions which does not require ground truth explanations. We achieve this through a novel explanation-driven data augmentation (EDDA) technique that augments the training…
Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation
West Virginia University（西弗吉尼亚大学）；Rochester Institute of Technology（罗彻斯特理工学院）；O Analytics（O分析公司）；University of Aberdeen（阿伯丁大学）；Fogsphere (Redev.AI Ltd, UK)（Fogsphere（Redev.AI有限公司，英国））；University College London（伦敦大学学院）
Nantes Université（南特大学）；Centrale Nantes（南特中央理工学院）；CNRS（法国国家科学研究中心）；Nantes University Hospital（南特大学医院）；Inserm（法国国家健康与医学研究院）
An important limitation to the development of AI-based solutions for In Vitro Fertilization (IVF) is the black-box nature of most state-of-the-art models, due to the complexity of deep learning architectures, which raises potential bias and fairness issues. The need for interpretable AI has risen not only in the IVF field but also in the deep learning community in general. This has started a trend in literature where authors focus on designing objective metrics to evaluate generic explanation methods. In this paper, we study the behavior of recently proposed objective faithfulness metrics appl…
AI systems' ability to explain their reasoning is critical to their utility and trustworthiness. Deep neural networks have enabled significant progress on many challenging problems such as visual question answering (VQA). However, most of them are opaque black boxes with limited explanatory capability. This paper presents a novel approach to developing a high-performing VQA system that can elucidate its answers with integrated textual and visual explanations that faithfully reflect important aspects of its underlying reasoning while capturing the style of comprehensible human explanations. Ext…
On the Faithfulness of Post-Hoc Concept Bottleneck Models
Institute of Data Science, German Aerospace Center（数据科学研究所，德国航空航天中心）；Computer Vision Group Jena, Friedrich Schiller University Jena（贾恩计算机视觉小组，弗里德里希·席勒大学贾恩）；GEOMAR Helmholtz Centre for Ocean Research Kiel（基尔海洋研究赫尔姆霍茨中心）
National University of Singapore（新加坡国立大学）；Institut de Robòtica i Informàtica Industrial, CSIC-UPC（西班牙国家研究委员会-加泰罗尼亚理工大学工业机器人与信息技术研究所）
Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic error (bias) by perturbations and corruptions. Furthermore, the distortions persist despite model fine-tuning on images biased by different factors (blur, color temperature, day/night). We present Debiased-CAM to recover explanation faithfulness across various bias types and levels by training a multi-input, multi-task model with auxiliary tasks for explanati…
University of British Columbia（不列颠哥伦比亚大学）；Huawei（华为）
The opacity of deep learning models constrains their debugging and improvement. Augmenting deep models with saliency-based strategies, such as attention, has been claimed to help get a better understanding of the decision-making process of black-box models. However, some recent works challenged saliency's faithfulness in the field of Natural Language Processing (NLP), questioning attention weights' adherence to the true decision-making process of the model. We add to this discussion by evaluating the faithfulness of in-model saliency applied to a video processing task for the first time, namel…
Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations. We illustrate a previously unrecognized limitation of the popular neural network explanation method Grad-CAM: as a side effect of the gradient averaging step, Grad-CAM sometimes highlights locations the model did not actually use. To solve this problem, we propose HiResCAM, a novel class-specific explanation method that is guaranteed to highlight only the locations the model used to make each prediction. We prove that HiResCAM is a generalization of CAM and explor…
City University of Hong Kong（香港城市大学）；National University of Singapore（新加坡国立大学）；The Hong Kong Polytechnic University（香港理工大学）
Attention mechanisms are dominating the explainability of deep models. They produce probability distributions over the input, which are widely deemed as feature-importance indicators. However, in this paper, we find one critical limitation in attention explanations: weakness in identifying the polarity of feature impact. This would be somehow misleading -- features with higher attention weights may not faithfully contribute to model predictions; instead, they can impose suppression effects. With this finding, we reflect on the explainability of current attention-based techniques, such as Atten…
Self-explaining deep models are designed to learn the latent concept-based explanations implicitly during training, which eliminates the requirement of any post-hoc explanation generation technique. In this work, we propose one such model that appends an explanation generation module on top of any basic network and jointly trains the whole module that shows high predictive performance and generates meaningful explanations in terms of concepts. Our training strategy is suitable for unsupervised concept learning with much lesser parameter space requirements compared to baseline methods. Our prop…
