AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Extending and Analyzing Self-Supervised Learning Across Domains

Bram Wallace, Bharath Hariharan

ECCV 2020 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 37 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
pretrain on all unlabeled data rather than only the labeled 10% (ablation)pretext + linear head · 10% label setting, 16 domainsaccuracy: drops an average of approximately 10%Improved
use Rotation instead of random initializationRotation · Katheraccuracy: 79% -> <60%Hurt
use Rotation pretext on domains lacking canonical orientation (Biological)Rotation · Biological groupaccuracyHurt
use Instance Discrimination instead of Rotation on Biological domainsInstance Discrimination · Biological groupaccuracyImproved
use pretext + linear head with 10% labels instead of full supervision on 10% labelsRotation · Internet and Scenes & Textures, 10% labelsaccuracyImproved
use Autoencoding pretext with 10% labelsAutoencoder · Biological, 10% labelsaccuracyImproved
use 2000 Jigsaw permutations instead of 100 or 10,000 (ablation)Jigsaw · 16 domainsaccuracyImproved
pretext test on unseen classes (pretext generalization) as predictor of downstream accuracyRotation · 16 domainsdownstream accuracyImproved
relate Instance Discrimination pretext loss to downstream accuracyInstance Discrimination · 16 domainsdownstream accuracyNo clear effect
use Jigsaw instead of Rotation/ID for random-label fitJigsaw · 16 domainsrandom vs normal label train accuracy correlation: 0.59 vs 0.46 vs 0.45Mixed

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