AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Learning Rare Category Classifiers on a Tight Labeling Budget

Ravi Teja Mullapudi, Fait Poms, William R. Mark, Deva Ramanan, Kayvon Fatahalian

ICCV 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 9 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 pseudo negative labels (machine-labeled easy negatives) when updating the deep representation (ablation)Ours (active semi-supervised rare category learner) · iNaturalist (50 rare categories)mean F1Improved
add background splitting to handle extreme imbalance (ablation)Ours · iNaturalist (50 rare categories)mean F1Improved
add frequent linear model updates between deep feature updates (B=10,Q=5 vs B=50,Q=1) (ablation)Ours · iNaturalist (50 rare categories)mean F1: N = 10, B = 50, Q = 1 -> N = 10, B = 10, Q = 5Improved
replace easy-negative-only pseudo labels with label propagation pseudo positives and negatives (DeepProp)Ours · iNaturalist (50 categories) and Places (20 categories)mean F1Hurt
replace easy-negative-only pseudo labels with deep model predictions as pseudo positives and negatives (KD-Semi)Ours · iNaturalist (50 categories) and Places (20 categories)mean F1Hurt
raise KD-Semi confidence threshold for pseudo positives from 0.90 to 0.98KD-Semi · iNaturalist (50 categories)false positive rate of automatic positives: 0.90 -> 0.95 -> 0.98Mixed
add deep feature updating (Ours) over frozen features (Tropel) with a deep model trained on pseudo negativesTropel · iNaturalist (50 categories) and Places (20 categories)mean F1Improved
train a deep model only on human labels (Tropel-Deep) instead of a linear model on frozen featuresTropel · iNaturalist (50 categories)mean F1Hurt
start from self-supervised SwAV representations (ImageNet or iNaturalist) instead of supervised ImageNet pretrainingOurs · iNaturalist (50 categories)mean F1Hurt
add deep feature updating to self-supervised representations (Ours-Self vs Tropel-Self)Tropel-Self · iNaturalist (50 categories)mean F1Improved

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