AI Paper Atlas

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

Pseudo-Loss Confidence Metric for Semi-Supervised Few-Shot Learning

Kai Huang, Jie Geng, Wen Jiang, Xinyang Deng, Zhe Xu

ICCV 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 69 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 selected filter (ablation)PLCM · step 10 of multi-step training, mini-ImageNet 5-wayaccuracy (%): 78.8 -> 83.7Improved
add selected filter (ablation)PLCM · step 9 of multi-step training, mini-ImageNet 5-wayaccuracy (%): 79.1 -> 83.3Improved
add selected filter (ablation)PLCM · step 10 of multi-step trainingerror rate of selected samples (%): 20.4 -> 13.2Improved
add selected filter (ablation)PLCM · step 3 of multi-step trainingaccuracy (%): 80.5 -> 80.1Hurt
add class-apart selection to class weight (ablation)PLCM · mini-ImageNet 5-way 1-shot (base SSFSL)accuracy (%): 68.28 -> 72.06Improved
add class weight to class-apart selection (ablation)PLCM · mini-ImageNet 5-way 1-shot (base SSFSL)accuracy (%): 71.76 -> 72.06Improved
add class-apart selection to class weight (ablation)PLCM · mini-ImageNet 5-way 5-shot (base SSFSL)accuracy (%): 78.19 -> 83.71Improved
add class weight to class-apart selection (ablation)PLCM · mini-ImageNet 5-way 5-shot (base SSFSL)accuracy (%): 83.03 -> 83.71Improved
add class-apart selection to class weight (ablation)ICI · mini-ImageNet 5-way 1-shot (base SSFSL)accuracy (%): 64.42 -> 70.07Improved
add class-apart selection to class weight (ablation)LST · mini-ImageNet 5-way 1-shot (base SSFSL)accuracy (%): 65.58 -> 70.55Improved
add multi-step training strategy (ablation)PLCM · mini-ImageNet 5-waytest accuracyImproved

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