AI Paper Atlas

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

Can contrastive learning avoid shortcut solutions?

Joshua David Robinson, Li Sun, Ke Yu, kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 14 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 IFM to MoCo-v2MoCo-v2 · ImageNet100top-1 accuracy: 80.4 -> 81.1Improved
Add IFM with ε=0.1MoCo-v2 · COPDGene, logFEV1ppR-square: 0.566 -> 0.615Improved
Add IFM with ε=0.1MoCo-v2 · COPDGene, CLEaccuracy: 49.6 -> 48.2Hurt
Add IFM with ε=0.1MoCo-v2 · COPDGene, mMRCaccuracy: 50.4 -> 50.4No clear effect
Use only the perturbed loss Lε rather than averaging it with standard contrastive loss (ablation)IFM · Classification tasksaverage score: 76.0% vs 75.9%Hurt
Re-normalize embeddings after perturbation (ablation)IFM-MoCo-v2 · STL10, CIFAR10, CIFAR100linear readout accuracy: STL10: 92.9% vs 92.9%; CIFAR10: 92.4% vs 92.2%; CIFAR100: 70.3% vs 70.1%No clear effect
Apply perturbations before normalization (ablation)IFM-MoCo-v2 · STL10, CIFAR10, CIFAR100linear readout accuracy: STL10: 92.9% vs 93.0%; CIFAR10: 92.4% vs 92.0%; CIFAR100: 70.3% vs 70.2%No clear effect
Adjust temperature or hard-negative concentration to make instance discrimination harderSimCLR · Trifeaturelinear readout accuracy across color, shape, and textureMixed
Use IFMSimCLR · Trifeaturelinear readout accuracy across color, shape, and textureImproved
Use IFMSimCLR · Robust-feature evaluation across tinyImageNet, STL10, CIFAR10, and CIFAR100accuracyImproved
Use IFM rather than SimCLRSimCLR · Non-robust-feature evaluation across tinyImageNet, STL10, CIFAR10, and CIFAR100average accuracy: 55.5% vs 56.7%No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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