Related papers: Probabilistic Conceptual Explainers: Trustworthy C…

Explainable machine learning significantly improves the transparency of deep neural networks. However, existing work is constrained to explaining the behavior of individual model predictions, and lacks the ability to transfer the…

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

The need for interpretable models has fostered the development of self-explainable classifiers. Prior approaches are either based on multi-stage optimization schemes, impacting the predictive performance of the model, or produce…

Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent…

Incorporating symmetry priors as inductive biases to design equivariant Vision Transformers (ViTs) has emerged as a promising avenue for enhancing their performance. However, existing equivariant ViTs often struggle to balance performance…

Explainability is a highly demanded requirement for applications in high-risk areas such as medicine. Vision Transformers have mainly been limited to attention extraction to provide insight into the model's reasoning. Our approach combines…

The increasing reliance on machine learning systems has made their security a critical concern. Evasion attacks enable adversaries to manipulate the decision-making processes of AI systems, potentially causing security breaches or…

High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without…

Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet their prediction process remains difficult to interpret because information is propagated through complex interactions across layers and attention heads.…

Vision Transformers (ViTs) have emerged as the state-of-the-art architecture in representation learning, leveraging self-attention mechanisms to excel in various tasks. ViTs split images into fixed-size patches, constraining them to a…

Background and Objective: Prototype-based methods improve interpretability by learning fine-grained part-prototypes; however, their visualization in the input pixel space is not always consistent with human-understandable biomarkers. In…

Attribution methods for Vision Transformers (ViTs) aim to identify image regions that influence model predictions, but producing faithful and well-localized attributions remains challenging. Existing attribution methods face several…

The present study explores the interpretability of latent spaces produced by time series foundation models, focusing on their potential for visual analysis tasks. Specifically, we evaluate the MOMENT family of models, a set of…

Visual transformers have achieved remarkable performance in image classification tasks, but this performance gain has come at the cost of interpretability. One of the main obstacles to the interpretation of transformers is the…

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA.…

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…

This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the…

Vision Transformers (ViTs) and Swin Transformers (Swin) are currently state-of-the-art in computational pathology. However, domain experts are still reluctant to use these models due to their lack of interpretability. This is not…

The Abstraction and Reasoning Corpus (ARC) is a popular benchmark focused on visual reasoning in the evaluation of Artificial Intelligence systems. In its original framing, an ARC task requires solving a program synthesis problem over small…