paper-with-me

홈 › Papers

Disentangling Visual Transformers: Patch-level Interpretability for Image Classification

2025-02-24 · Guillaume Jeanneret, Loïc Simon, Frédéric Jurie

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 self-attention mechanism, which mixes visual information across the whole image in a complex way. In this paper, we propose Hindered Transformer (HiT), a novel interpretable by design architecture inspired by visual transformers. Our proposed architecture rethinks the design of transformers to better disentangle patch influences at the classification stage. Ultimately, HiT can be interpreted as a linear combination of patch-level information. We show that the advantages of our approach in terms of explicability come with a reasonable trade-off in performance, making it an attractive alternative for applications where interpretability is paramount.

📄 PDF Abstract BibTeX arXiv:2502.17196

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Patch-level Representation Learning for Self-supervised Vision Transformers

2022-06-16 · CVPR 2022 1 · Sukmin Yun, Hankook Lee, Jaehyung Kim, Jinwoo Shin

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural ad…

Instance Segmentationobject-detectionObject DetectionRepresentation Learning+3

ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder

2022-07-17 · ICML 2022 7 · Sangwon Kim; Jaeyeal Nam; Byoung Chul Ko

Vision transformers (ViTs), which have demonstrated a state-of-the-art performance in image classification, can also visualize global interpretations through attention-based contributions. How- ever, the complexity of th…

Decision MakingDecoderFine-Grained Image ClassificationFine-Grained Visual Categorization+2

IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers

2021-06-23 · NeurIPS 2021 12 · Bowen Pan, Rameswar Panda, Yifan Jiang, Zhangyang Wang 외

The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. In spite of the impressive success made by transformers in a variety of vision tasks, it still suffe…

Efficient ViTs

Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP

2026-04-07 · Yusung Ro, Jaehyun Choi, Junmo Kim arxiv

Sparse Autoencoders (SAEs) have emerged as a powerful tool for interpreting the internal representations of CLIP vision encoders, yet existing analyses largely focus on the semantic meaning of individual features. We int…

Visual Interpretability for Deep Learning: a Survey

2018-02-02 · Quanshi Zhang, Song-Chun Zhu

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited su…

Deep LearningExplainable artificial intelligenceSurvey