Recent work has explored how individual components of the CLIP-ViT model contribute to the final representation by leveraging the shared image-text representation space of CLIP. These components, such as attention heads and MLPs, have been shown to capture distinct image features like shape, color or texture. However, understanding the role of these components in arbitrary vision transformers (ViTs) is challenging. To this end, we introduce a general framework which can identify the roles of various components in ViTs beyond CLIP. Specifically, we (a) automate the decomposition of the final representation into contributions from different model components, and (b) linearly map these contributions to CLIP space to interpret them via text. Additionally, we introduce a novel scoring function to rank components by their importance with respect to specific features. Applying our framework to various ViT variants (e.g. DeiT, DINO, DINOv2, Swin, MaxViT), we gain insights into the roles of different components concerning particular image features. These insights facilitate applications such as image retrieval using text descriptions or reference images, visualizing token importance heatmaps, and mitigating spurious correlations. We release our code to reproduce the experiments at https://github.com/SriramB-98/vit-decompose

翻译：近期研究通过利用CLIP共享的图像-文本表示空间，探索了CLIP-ViT模型中各个组件（如注意力头和MLP）如何贡献于最终表示，这些组件已被证明能捕获形状、颜色或纹理等不同的图像特征。然而，理解这些组件在任意视觉Transformer（ViT）中的作用仍具挑战性。为此，我们提出了一个通用框架，能够识别超越CLIP范围的各种ViT中不同组件的作用。具体而言，我们（a）自动化地将最终表示分解为来自不同模型组件的贡献，（b）将这些贡献线性映射到CLIP空间以通过文本进行解释。此外，我们引入了一种新颖的评分函数，可根据组件对特定特征的重要性进行排序。通过将我们的框架应用于多种ViT变体（如DeiT、DINO、DINOv2、Swin、MaxViT），我们获得了关于不同组件在特定图像特征中作用的深入理解。这些见解促进了多种应用，例如使用文本描述或参考图像进行图像检索、可视化令牌重要性热图以及减轻虚假相关性。我们在https://github.com/SriramB-98/vit-decompose 发布了复现实验的代码。