AI Paper Atlas

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

Contrastive Learning with Adversarial Examples

Chih-Hui Ho, Nuno Nvasconcelos

NeurIPS 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training with feature consistency · 61 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
Add adversarial augmentation and adversarial training to Plain contrastive learningPlain · CIFAR10, CIFAR100, tinyImageNetdownstream classification accuracy: 82.78$\pm$0.20 -> 83.09$\pm$0.19; 54.73$\pm$0.20 -> 55.28$\pm$0.12; 79.65$\pm$0.43 -> 79.94$\pm$0.28; 51.82$\pm$0.46 -> Improved
Add adversarial augmentation and adversarial training to UELUEL · CIFAR10, CIFAR100, tinyImageNetdownstream classification accuracy: 83.63$\pm$0.14 -> 84$\pm$0.15; 55.23$\pm$0.28 -> 55.96$\pm$0.06; 80.63$\pm$0.18 -> 80.94$\pm$0.13; 52.99$\pm$0.25 -> 54.Improved
Add adversarial augmentation and adversarial training to SimCLRSimCLR · CIFAR10, CIFAR100, tinyImageNetdownstream classification accuracy: 75.92$\pm$0.26 -> 76.45$\pm$0.32; 34.94$\pm$0.25 -> 38.89$\pm$0.25; 83.27$\pm$0.17 -> 83.32$\pm$0.26; 53.79$\pm$0.21 -> Improved
Use ε=0.07 rather than ε=0.03 (ablation)CLAE · CIFAR10, CIFAR100, tinyImageNetdownstream classification accuracy: 83.09$\pm$0.19 -> 83.04$\pm$0.18; 55.28$\pm$0.12 -> 54.96$\pm$0.12; 79.94$\pm$0.28 -> 79.85$\pm$0.16; 52.04$\pm$0.32 -> Mixed
Increase batch size (ablation)SimCLR and SimCLR CLAE · CIFAR100downstream classification accuracyImproved
Use adversarial training at batch size 64 rather than the baseline at batch size 256 (ablation)SimCLR CLAE vs SimCLR · CIFAR100downstream classification accuracy: 53.79\% -> 54\%Improved
Vary embedding dimension (ablation)SimCLR and SimCLR CLAE · CIFAR100downstream classification accuracyNo clear effect
Use a larger ResNet architecture (ablation)SimCLR CLAE · CIFAR100downstream classification accuracy improvement: 5\%Improved
Increase the adversarial loss weight α from 0 to around 0.8 (ablation)SimCLR CLAE · CIFAR100downstream classification accuracyImproved
Increase α beyond 0.2, up to 2 (ablation)SimCLR CLAE · CIFAR100downstream classification accuracyNo clear effect
Increase attack strength ε across the tested range (ablation)SimCLR CLAE · CIFAR100downstream classification accuracyNo clear effect
Train for more pretext epochs (ablation)SimCLR and SimCLR CLAE · CIFAR100downstream classification accuracy: 300 epochs vs baseline 400 epochs; 400 epochs vs baseline 500 epochsImproved

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