相关论文: VISION DIFFMASK: Faithful Interpretation of Vision…

Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…

Vision Transformers are at the heart of the current surge of interest in foundation models for histopathology. They process images by breaking them into smaller patches following a regular grid, regardless of their content. Yet, not all…

Image anomaly detection consists in detecting images or image portions that are visually different from the majority of the samples in a dataset. The task is of practical importance for various real-life applications like biomedical image…

Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in…

Attribution methods assess the contribution of inputs to the model prediction. One way to do so is erasure: a subset of inputs is considered irrelevant if it can be removed without affecting the prediction. Though conceptually simple,…

Recent advancements in Vision Transformers (ViT) have demonstrated exceptional results in various visual recognition tasks, owing to their ability to capture long-range dependencies in images through self-attention mechanisms. However, the…

This work aims to reproduce the results of Faithful Vision Transformers (FViTs) proposed by arXiv:2311.17983 alongside interpretability methods for Vision Transformers from arXiv:2012.09838 and Xu (2022) et al. We investigate claims made by…

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…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations. A new line of work on improving model interpretability has just started, and…

The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multimodal image-language transformer models. The evaluation is…

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

Most existing interpretable methods explain a black-box model in a post-hoc manner, which uses simpler models or data analysis techniques to interpret the predictions after the model is learned. However, they (a) may derive contradictory…

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…

With abundant, unlabeled real faces, how can we learn robust and transferable facial representations to boost generalization across various face security tasks? We make the first attempt and propose FS-VFM, a scalable self-supervised…

To interpret Vision Transformers, post-hoc explanations assign salience scores to input pixels, providing human-understandable heatmaps. However, whether these interpretations reflect true rationales behind the model's output is still…

Visuomotor imitation learning policies enable robots to efficiently acquire manipulation skills from visual demonstrations. However, as scene complexity and visual distractions increase, policies that perform well in simple settings often…

With the rise of large-scale foundation models, efficiently adapting them to downstream tasks remains a central challenge. Linear probing, which freezes the backbone and trains a lightweight head, is computationally efficient but often…

Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, one can design systematic experiments and/or inspect the…

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…