paper-with-me

Papers

Understanding The Robustness in Vision Transformers

2022-04-26 · Daquan Zhou, Zhiding Yu, Enze Xie, Chaowei Xiao, Anima Anandkumar, Jiashi Feng, Jose M. Alvarez

Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic understanding. In this paper, we examine the role of self-attention in learning robust representations. Our study is motivated by the intriguing properties of the emerging visual grouping in Vision Transformers, which indicates that self-attention may promote robustness through improved mid-level representations. We further propose a family of fully attentional networks (FANs) that strengthen this capability by incorporating an attentional channel processing design. We validate the design comprehensively on various hierarchical backbones. Our model achieves a state-of-the-art 87.1% accuracy and 35.8% mCE on ImageNet-1k and ImageNet-C with 76.8M parameters. We also demonstrate state-of-the-art accuracy and robustness in two downstream tasks: semantic segmentation and object detection. Code is available at: https://github.com/NVlabs/FAN.

📄 PDF Abstract BibTeX arXiv:2204.12451

Code (2)

nvlabs/fan 공식 구현 pytorch
NVlabs/STL pytorch

Tasks

Domain GeneralizationImage Classificationobject-detectionObject DetectionSemantic Segmentation

Similar Papers 제목 키워드 기반

Understanding Adversarial Robustness of Vision Transformers via Cauchy Problem

2022-08-01 · Zheng Wang, Wenjie Ruan

Recent research on the robustness of deep learning has shown that Vision Transformers (ViTs) surpass the Convolutional Neural Networks (CNNs) under some perturbations, e.g., natural corruption, adversarial attacks, etc. …

Adversarial Robustness

Simplicity Bias of Transformers to Learn Low Sensitivity Functions

2024-03-11 · Bhavya Vasudeva, Deqing Fu, Tianyi Zhou, Elliott Kau 외

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of the inductive biases that they have and how those biases are different from other neural network architectures rema…

Sensitivity

On the interplay of adversarial robustness and architecture components: patches, convolution and attention

2022-09-14 · Francesco Croce, Matthias Hein

In recent years novel architecture components for image classification have been developed, starting with attention and patches used in transformers. While prior works have analyzed the influence of some aspects of archi…

Adversarial Robustnessimage-classificationImage Classification

Are Vision Transformers Robust to Spurious Correlations?

2022-03-17 · Soumya Suvra Ghosal, Yifei Ming, Yixuan Li

Deep neural networks may be susceptible to learning spurious correlations that hold on average but not in atypical test samples. As with the recent emergence of vision transformer (ViT) models, it remains underexplored h…

Understanding vision transformer robustness through the lens of out-of-distribution detection

2026-02-01 · Joey Kuang, Alexander Wong arxiv

Vision transformers have shown remarkable performance in vision tasks, but enabling them for accessible and real-time use is still challenging. Quantization reduces memory and inference costs at the risk of performance l…

Out-of-Distribution DetectionData Augmentation