AI Paper Atlas

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

RDA: Reciprocal Distribution Alignment for Robust Semi-Supervised Learning

Yue Duan, Lei Qi, Lei Wang, Luping Zhou, Yinghuan Shi

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 17 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
use RDA instead of CoMatch with scarce labelsFixMatch-style SSL · CIFAR-10 (20 labels, matched)accuracy: 88.43 -> 92.03Improved
use RDA instead of CoMatchSSL · mini-ImageNet (1000 labels, matched)accuracy: 43.72 -> 46.91Improved
use RDA instead of CoMatch with 100 labelsSSL · CIFAR-10 (100 labels, matched)accuracy: 94.55 -> 94.35No clear effect
add original distribution alignment to FixMatch under imbalanced labeled dataFixMatch · CIFAR-10 (40 labels, imbalanced labeled N0=10)accuracy: 85.72 -> 71.23Hurt
use RDA instead of FixMatch under imbalanced labeled dataFixMatch · CIFAR-10 (40 labels, imbalanced labeled N0=10)accuracy: 85.72 -> 92.57Improved
use RDA instead of CoMatch under imbalanced labeled dataCoMatch · CIFAR-10 (40 labels, imbalanced labeled N0=10)accuracy: 60.27 -> 92.57Improved
use RDA instead of FixMatch under imbalanced labeled dataFixMatch · CIFAR-100 (400 labels, imbalanced labeled N0=40)accuracy: 25.66 -> 30.86Improved
use RDA instead of DARPDARP protocol · CIFAR-10 DARP protocol (gamma_l=100, gamma_u=1)accuracy: 85.40 -> 93.35Improved
use RDA instead of DARPDARP protocol · STL-10 DARP protocol (gamma_l=10)accuracy: 77.80 -> 87.21Improved
use reciprocal alignment of both directions instead of aligning only complementary predictions to reversed class predictions (ablation)RDA · CIFAR-10 (40 labels, imbalanced labeled N0=20)accuracy: 58.90 -> 81.78Improved
use reciprocal alignment of both directions instead of aligning only class predictions to reversed complementary predictions (ablation)RDA · CIFAR-10 (40 labels, imbalanced labeled N0=20)accuracy: 73.54 -> 81.78Improved
use reciprocal alignment in the conventional matched setting (ablation)RDA · CIFAR-10 (40 labels, matched)accuracy: 93.35 -> 94.13No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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