AI Paper Atlas

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

PSS: Progressive Sample Selection for Open-World Visual Representation Learning

Tianyue Cao, Yongxin Wang, Yifan Xing, Tianjun Xiao, Tong He, Zheng Zhang, Hao Zhou, Joseph Tighe

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 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 sample selection to iterative training (ablation)PSS · iNaturalist retrievalRecall@1: 0.5548 -> 0.5714Improved
add iterative refinement to sample selection (ablation)PSS · iNaturalist retrievalRecall@1: 0.5522 -> 0.5714Improved
add sample selection (fewer training images) (ablation)PSS · iNaturalist retrievaltraining data: 325,846 -> 87,349Improved
add sample selection with one-step training (ablation)Hi-LANDER pseudo-labelling · iNaturalist retrievalRecall@1: 0.5421 -> 0.5522Improved
train on selected samples far from labeled classes instead of close ones (ablation)PSS · iNaturalist retrieval (iteration 1)Recall@1: 0.5490 -> 0.5524Improved
add progressive selection instead of all-data iterations (DeepClustering)PSS · iNaturalist retrievalRecall@1: 0.5548 -> 0.5714Improved
add progressive selection instead of DeepClusteringPSS · IJB-C face verificationFNMR@FMR 1e-4: 0.2234 -> 0.2165Improved
add open-set UNO pseudo labels to supervised baselineUNO · iNaturalist retrievalRecall@1: 0.5376 -> 0.5372Hurt
add pseudo labeling (all unlabeled data at once)Supervised baseline · iNaturalist retrievalRecall@1: 0.5376 -> 0.5447Improved

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