Improving Robustness of Vision Transformers by Reducing Sensitivity to Patch Corruptions-Reference-Cited by-同舟云学术

Improving Robustness of Vision Transformers by Reducing Sensitivity to Patch Corruptions

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Guo Yong¹,Stutz David¹,Schiele Bernt¹

Affiliation:

1. Max Planck Institute for Informatics, Saarland Informatics Campus

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10203037/10203050/10204027.pdf?arnumber=10204027

Reference61 articles.

1. Patch-fool: Are vision transformers always robust against adversarial perturbations?;fu;Proc of the International Conference on Learning Representations (ICLR),0

2. Theoretically principled trade-off between robustness and accuracy;zhang;Proc of the International Conference on Machine Learning (ICML),0

3. Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

4. Are vision transformers robust to patch perturbations?;gu;Proc Of the European Conference on Computer Vision (ECCV),0

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Fuzzy preference matroids rough sets for approximate guided representation in transformer;Expert Systems with Applications;2024-12

2. Semi-hard constraint augmentation of triplet learning to improve image corruption classification;The Visual Computer;2024-06-18

3. Robustifying Token Attention for Vision Transformers;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

4. Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

5. HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06