AI Paper Atlas

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

Decoupled Adversarial Contrastive Learning for Self-Supervised Adversarial Robustness

Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Axi Niu, Jiu Feng, Chang D. Yoo, In So Kweon

ECCV 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training recipes · 20 citations (OpenAlex)

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
use two-stage decoupled training (DeACL) instead of single-stage AdvCLadversarial contrastive learning · CIFAR10 (SLF)AutoAttack accuracy (%): 42.57 -> 45.31Improved
use DeACL instead of AdvCL for pretraining costadversarial contrastive learning · CIFAR10total GPU-days: 12.60 -> 0.45Improved
use DeACL instead of AdvCLadversarial contrastive learning · CIFAR100 (SLF)standard accuracy (%): 48.34 -> 52.79Improved
raise stage-2 weight decay from 1e-6 to 5e-4 (ablation)DeACL stage 2 · CIFAR10 (SLF)AutoAttack accuracy (%): 34.77 -> 45.31Improved
raise stage-2 weight decay from 5e-4 to 5e-3 (ablation)DeACL stage 2 · CIFAR10 (SLF)AutoAttack accuracy (%): 45.31 -> 24.80Hurt
use strong augmentation on both clean and adversarial examples at stage 2 (ablation)DeACL stage 2 · CIFAR10 (SLF)AutoAttack accuracy (%): 45.31 -> 6.93Hurt
use strong augmentation on clean examples only at stage 2 (ablation)DeACL stage 2 · CIFAR10 (SLF)AutoAttack accuracy (%): 45.31 -> 34.47Hurt
add projector head at stage 2 (ablation)DeACL stage 2 · CIFAR10 (SLF)AutoAttack accuracy (%): 45.31 -> 42.48Hurt
add contrastive collapse prevention at stage 2 (ablation)DeACL stage 2 · CIFAR10 (SLF)AutoAttack accuracy (%): 45.31 -> 34.18Hurt
initialise student from pretrained stage-1 weights rather than scratch (ablation)DeACL stage 2 · CIFAR10 (SLF)AutoAttack accuracy (%): 44.63 -> 45.31No clear effect
swap SimCLR for MoCo v2 at stage 1 (ablation)DeACL stage 1 · CIFAR10 (SLF)AutoAttack accuracy (%): 45.31 -> 46.29No clear effect
swap SimCLR for BarlowTwins at stage 1 (ablation)DeACL stage 1 · CIFAR10 (SLF)AutoAttack accuracy (%): 45.31 -> 41.31Hurt

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