AI Paper Atlas

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

Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning

Xingping Dong, Jianbing Shen, Ling Shao

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection

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
replace ACAI/DC embedding with clustering-friendly embedding (CFE) for k-means pseudo-labelsCACTUs-MAML · Omniglot 5-way 1-shotaccuracy: 68.84 -> 91.32Improved
replace DC embedding with CFECACTUs-MAML · miniImageNet 5-way 1-shotaccuracy: 39.90 -> 41.99Improved
add negative set without asynchronous embedding (ablation)CFE-M (positive set only) · miniImageNet 5-way 1-shotaccuracy: 39.75 -> 25.35Hurt
add asynchronous (momentum) encoder to positive set (ablation)CFE-M · miniImageNet 5-way 1-shotaccuracy: 39.75 -> 41.04Improved
add negative set with asynchronous embedding (ablation)CFE-M (Pos+AE) · miniImageNet 5-way 1-shotaccuracy: 41.04 -> 41.99Improved
add cluster selection (SC) from progressive evaluation (ablation)CFE-M (Pos+Neg+AE) · miniImageNet 5-way 1-shotaccuracy: 41.99 -> 43.39Improved
add noise filtering (FN) on top of cluster selection (ablation)CFE-M (Pos+Neg+AE+SC) · miniImageNet 5-way 1-shotaccuracy: 43.39 -> 43.60Improved
add noise filtering without cluster selection (ablation)CFE-M (Pos+Neg+AE) · miniImageNet 5-way 1-shotaccuracy: 41.99 -> 42.85Improved
add progressive evaluation (SC+FN) to EP (ablation)CFE-E (Pos+Neg+AE) · miniImageNet 5-way 1-shotaccuracy: 47.55 -> 49.13Improved
use CFE (Pos+Neg+AE) instead of MoCo-v2 embedding for pseudo-labelsMAML · miniImageNet 5-way 1-shotaccuracy: 39.83 -> 41.99Improved
use CFE pseudo-labels with EP instead of CACTUs-EPEP · Omniglot 20-way 1-shotaccuracy: 53.50 -> 83.67Improved
use PL-CFE-MAML instead of supervised MAML on many-shot tasksMAML · miniImageNet 5-way 50-shotaccuracy: 73.77 -> 75.52Improved

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