AI Paper Atlas

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

Learning to Learn in a Semi-Supervised Fashion

Yun-Chun Chen, Chao-Te Chou, Yu-Chiang Frank Wang

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 5 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 semantics-oriented meta-learning stage on the full labeled training setBoT · Market-1501 (fully supervised, all IDs)Rank-1 (%): 94.5 -> 94.8Improved
add semantics-oriented meta-learning stage on the full labeled training setAlignedReID · Market-1501 (fully supervised, all IDs)Rank-1 (%): 89.2 -> 91.1Improved
add semantics-oriented meta-learning stage on the full labeled training setAlignedReID · DukeMTMC-reID (fully supervised, all IDs)Rank-1 (%): 79.3 -> 81.7Improved
add semantics-oriented meta-learning stage on the full labeled training setBoT · DukeMTMC-reID (fully supervised, all IDs)Rank-1 (%): 86.4 -> 86.6Improved
increase labeled category ratio from 25% to 75% (ablation)semi-supervised retrieval · Car196 retrievalRecall@1 (%): 54.5 -> 65.9Improved
increase labeled category ratio from 25% to 75% (ablation)semi-supervised retrieval · CUB-200 retrievalRecall@1 (%): 48.4 -> 51.0Improved
increase labeled ID ratio from 1/12 to 1/3 (ablation)semi-supervised re-ID · Market-1501 (semi-supervised)Rank-1 (%): 56.7 -> 80.3Improved
use meta-learned pseudo-labels instead of clustering-based pseudo labelsMVC · Market-1501 (semi-supervised, 1/3 IDs labeled)Rank-1 (%): 72.2 -> 80.3Improved
use meta-learned pseudo-labels instead of clustering-based pseudo labelsMVC · DukeMTMC-reID (semi-supervised, 1/3 IDs labeled)Rank-1 (%): 52.9 -> 67.5Improved
apply the meta-learning strategy to limited labeled data onlyPyrNet · Market-1501 (fully supervised, 1/3 of IDs)Rank-1 (%): 74.9 -> 77.0Improved
apply the meta-learning strategy to limited labeled data onlyMGN · Market-1501 (fully supervised, 1/12 of IDs)Rank-1 (%): 50.6 -> 53.4Improved
use 25% labeled categories with meta-learned pseudo labels instead of unsupervised InstanceInstance · Car196 retrievalRecall@1 (%): 41.3 -> 54.5Improved

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