AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond

Yi Yu, Wenhan Yang, Yap-Peng Tan, Alex C. Kot

CVPR 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 53 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Integrate robust modules and adversarial lossMPRNet · RainCityscape, LMSE attackmIoU: 0.3945 -> 0.7592Improved
Add adversarial loss (ablation)RCDNet · Rain100H, LMSE attackPSNR: 12.29 -> 21.85Improved
Add adversarial loss (ablation)RCDNet · Rain100H, clean inputSSIM: 0.8867 -> 0.8584Hurt
Add attention, specifically SE with addition (ablation)RCDNet · RainCityscape, LMSE attackmIoU: 0.1924 -> 0.3502Improved
Add attention, specifically SE with addition (ablation)RCDNet · RainCityscape, LPIPS attackAP: 0.5427 -> 0.6730Mixed
Remove rain-mask side information (ablation)JORDER-E · RainCityscape, LMSE attackPSNR: 12.89 -> 14.89Improved
Remove rain-mask side information (ablation)JORDER-E · RainCityscape, LMSE attackAP: 0.6511 -> 0.6202Hurt
Keep the larger receptive field with dilation paths {1,2,3} (ablation)JORDER-E · Rain100H, LMSE attackPSNR: 9.32 -> 10.91Improved
Add three recurrent blocks (ablation)Ours · RainCityscape, LMSE attackmIoU: 0.6512 -> 0.7592Improved
Add diverse dilations (ablation)Ours · RainCityscape, LMSE attackmIoU: 0.7011 -> 0.7592Improved
Add attention module (ablation)Ours · RainCityscape, LMSE attackmIoU: 0.3062 -> 0.7592Improved
Add adversarial loss (ablation)Ours · RainCityscape, LMSE attackmIoU: 0.4745 -> 0.7592Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy