AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Multitask Learning Strengthens Adversarial Robustness

Chengzhi Mao, Amogh Gupta, Vikram Nitin, Baishakhi Ray, Shuran Song, Junfeng Yang, Carl Vondrick

ECCV 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis

Read the paperCheck 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
add depth and auto-encoder auxiliary tasks to segmentation training (ablation)DRN-22 segmentation · Cityscapes PGD100mIoU: 10.15 -> 11.52Improved
add auto-encoder task to segmentation (ablation)DRN-22 segmentation · Cityscapes Houdini100mIoU: 5.04 -> 6.24Improved
add auxiliary tasks to training (single-task attack)DRN-22 segmentation · CityscapesmIoU / abs error: segmentation mIoU improves by 1.2 points and depth by 11% under attackImproved
add segmentation task to depth training (ablation)DRN-22 depth · Cityscapes PGD100abs error: 10.8 -> 9.69Improved
add auxiliary tasks to training (ablation)DRN-22 · Cityscapes cleanmIoU: 48.58 -> 48.61No clear effect
add auxiliary tasks to trainingResNet-18 on 11 Taskonomy tasks · Taskonomy PGD L_inf=4 50 stepstask performance: 10.23% relative improvementImproved
add auxiliary tasks to trainingResNet-18 on 11 Taskonomy tasks · Taskonomy cleantask performance: average improvement of 4.7%Improved
add multi-task learning to adversarial trainingDRN-22 · Cityscapes adversarial trainingmIoU / abs error: segmentation mIoU improves by 2.40 points and depth improves by 8.4%Improved
add depth task to adversarially trained segmentation (ablation)DRN-22 · Cityscapes adversarial training Houdini100mIoU: 17.05 -> 19.45Improved
add auxiliary tasks under multi-task PGD attack (ablation)DRN-D-105 · Cityscapes PGDmIoU: 15.75 -> 16.36Improved
add auxiliary tasks under multi-task PGD attack (ablation)DRN-D-105 · Cityscapes PGDdepth abs error: 6.81 -> 5.81Improved
increase number of output dimensions (random pixel subset of segmentation output) (ablation)DRN-105 · Cityscapes FGSM/PGDrobustnessImproved

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