AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Unbiased Supervised Contrastive Learning

Carlo Alberto Barbano, Benoit Dufumier, Enzo Tartaglione, Marco Grangetto, Pietro Gori

ICLR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 4 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
replace SupCon with ε-SupInfoNCEResNet-50 · CIFAR-10top-1 accuracy: 95.64\std{0.02} -> 96.14\std{0.01}Improved
replace SupCon with ε-SupInfoNCEResNet-50 · CIFAR-100top-1 accuracy: 75.41\std{0.19} -> 76.04\std{0.01}Improved
replace ε-SupCon with ε-SupInfoNCEResNet-50 · ImageNet-100top-1 accuracy: 82.83\std{0.11} -> 83.3\std{0.06}Improved
add FairKL to ε-SupInfoNCEε-SupInfoNCE · Biased-MNISTtop-1 accuracy: 33.16\std{3.57} -> 90.51\std{1.55} at ρ=0.999; 73.86\std{0.81} -> 96.19\std{0.23} at ρ=0.997; 83.65\std{0.36} -> 97.00\sImproved
add FairKL to ε-SupInfoNCEε-SupInfoNCE · Corrupted CIFAR-10 and bFFHQtop-1 accuracy: 33.33\std{0.38}, 36.53\std{0.38}, 41.45\std{0.42}, 50.73\std{0.90}; bFFHQ 64.8\std{0.43}Mixed
add FairKL to ε-SupInfoNCEε-SupInfoNCE · 9-Class ImageNet UNB and ImageNet-Atop-1 accuracy: UNB 94.1\std{0.3} -> 94.8\std{0.3}; ImageNet-A 34.1\std{0.6} -> 35.7\std{0.5}Improved
add a projection head (ablation)ε-SupInfoNCE + FairKL · Corrupted CIFAR-10top-1 accuracy: 33.33\std{0.38} -> 30.85\std{0.19}; 36.53\std{0.38} -> 32.75\std{0.57}; 41.45\std{0.42} -> 37.95\std{0.14}; 50.73\std{0.Hurt
use full FairKL, including distance-distribution variance constraints, rather than mean-only FairKL (ablation)ε-SupInfoNCE + FairKL · Corrupted CIFAR-10 and bFFHQtop-1 accuracy: 32.37\std{1.72} -> 33.33\std{0.38}; 35.65\std{0.75} -> 36.53\std{0.38}; 39.94\std{0.50} -> 41.45\std{0.42}; 50.25\std{0.Improved
use ε-SupInfoNCE instead of ε-SupConsupervised contrastive learning · Biased-MNIST ρ=0.999top-1 accuracy: 24.36\std{3.23} -> 33.16\std{3.57}Improved
use ε-SupInfoNCE instead of ε-SupConsupervised contrastive learning · Biased-MNIST ρ≤0.997top-1 accuracy: ρ=0.997: 74.35\std{0.09} vs 73.86\std{0.81}; ρ=0.995: 84.13\std{1.31} vs 83.65\std{0.36}; ρ=0.99: 91.12\std{0.35} vs 91.Mixed
add a small cross-entropy contribution during end-to-end training (ablation)FairKL debiasing training · biased datasetsaccuracyNo clear effect
use a larger batch size and weight decay in the bFFHQ setup (ablation)ε-SupInfoNCE debiasing · bFFHQaccuracy: 54.8\% without FairKL; 56.87\% for the vanilla modelNo clear effect

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