paper-with-me

Papers

Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP

2024-06-03 · Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi

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

📄 PDF Abstract BibTeX arXiv:2406.01583

Code (1)

sriramb-98/vit-decompose 공식 구현 pytorch

Tasks

Image Retrieval

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…
Multi-Head Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers

2026-06-04 · Tang Li, Yanlin Chen, Mengmeng Ma, Xi Peng arxiv

Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before safe deployment. Sparse autoencoders (SAEs) provide a promising lens …

Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features

2025-06-26 · Shangbo Wu, Yu-an Tan, Ruinan Ma, Wencong Ma 외

The ability of deep neural networks (DNNs) come from extracting and interpreting features from the data provided. By exploiting intermediate features in DNNs instead of relying on hard labels, we craft adversarial pertur…

Contrastive LearningSelf-Supervised Learning

Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception

2026-07-09 · Ludovica de Paolis, Marco Baroni, Alessandro Laio, Eugenio Piasini arxiv

In computational vision science, Convolutional Neural Networks (CNNs) have emerged as a popular model of biological vision because of the alignment they can exhibit with neural and behavioral data in humans and animals. …

Object Recognition

Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection

2026-04-29 · Ahyoung Oh, Wonseok Shin, Songkuk Kim arxiv

Sparse Autoencoders (SAEs) have demonstrated significant success in interpreting Large Language Models (LLMs) by decomposing dense representations into sparse, semantic components. However, their potential for analyzing …

Out-of-Distribution Detection

Representation Separation for Semantic Segmentation with Vision Transformers

2022-12-28 · Yuanduo Hong, Huihui Pan, Weichao Sun, Xinghu Yu 외

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region le…

Semantic Segmentation