AI Paper Atlas

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

Iterative Label Cleaning for Transductive and Semi-Supervised Few-Shot Learning

Michalis Lazarou, Tania Stathaki, Yannis Avrithis

ICCV 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 80 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 label propagation using unlabeled queries (transductive vs inductive) (ablation)iLPC · miniImageNet 1-shot transductive (WRN-28-10)accuracy (%): 68.17 -> 74.24Improved
add class balancing to label propagation (ablation)iLPC · miniImageNet 1-shot transductive (WRN-28-10)accuracy (%): 74.24 -> 79.42Improved
add iterative label cleaning to label propagation and balancing (ablation)iLPC · miniImageNet 1-shot transductive (WRN-28-10)accuracy (%): 79.42 -> 83.05Improved
add iterative label cleaning without balancing (ablation)LP · miniImageNet 1-shot transductive (WRN-28-10)accuracy (%): 74.24 -> 78.29Improved
replace iterative label cleaning with selecting column-wise maxima of P (iProb) (ablation)iLPC · miniImageNet 1-shot transductive (WRN-28-10)accuracy (%): 83.05 -> 80.75Hurt
replace label propagation with a linear classifier (ablation)iLPC · miniImageNet 1-shot transductive (WRN-28-10)accuracy (%): 83.05 -> 82.04Hurt
use true class prior for balancing instead of none in unbalanced queries (ablation)iLPC · miniImageNet 1-shot unbalanced transductiveaccuracy (%): 78.06 -> 82.68Improved
use uniform balancing when queries are unbalanced (ablation)iLPC · miniImageNet 1-shot unbalanced transductiveaccuracy (%): 78.06 -> 77.50Hurt
add PT+MAP feature pre-processing (power transform, normalization, centering) (ablation)PT+MAP · miniImageNet 1-shot transductiveaccuracy (%): 48.57 -> 82.88Improved
add PT+MAP feature pre-processing (power transform, normalization, centering) (ablation)iLPC · miniImageNet 1-shot transductiveaccuracy (%): 78.89 -> 83.05Improved
increase queries from 15 to 50 per classiLPC vs PT+MAP · miniImageNet 1-shot transductiveaccuracy (%): 83.05 -> 85.98Improved
use ResNet-12B with no augmentation or scaling, iLPC vs MCTiLPC vs MCT · miniImageNet 1-shot transductiveaccuracy (%): 75.58 vs 67.26Improved

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