# VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking Source: [VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:11:39.114Z Authors: Angelos Nalmpantis, Apostolos Panagiotopoulos, John Gkountouras, Konstantinos Papakostas, Wilker Aziz Published: 2023-04-13T10:49:26.000Z ## Abstract The lack of interpretability of the Vision Transformer may hinder its use in critical real-world applications despite its effectiveness. To overcome this issue, we propose a post-hoc interpretability method called VISION DIFFMASK, which uses the activations of the model's hidden layers to predict the relevant parts of the input that contribute to its final predictions. Our approach uses a gating mechanism to identify the minimal subset of the original input that preserves the predicted distribution over classes. We demonstrate the faithfulness of our method, by introducing a faithfulness task, and comparing it to other state-of-the-art attribution methods on CIFAR-10 and ImageNet-1K, achieving compelling results. To aid reproducibility and further extension of our work, we open source our implementation: https://github.com/AngelosNal/Vision-DiffMask ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()