VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking

CoRR(2023)

引用 2|浏览11
暂无评分
摘要
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
更多
查看译文
关键词
attribution methods,CIFAR-10 dataset,differentiable patch masking,faithful interpretation,faithfulness task,ImageNet-1K dataset,open source,post-hoc interpretability method,Vision DiffMask,vision transformers
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要