Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

2020/07/17 by Jaehyung Kim, Kim, Jaehyung, Youngbum Hur +9 · 3 citations
Computer Science · #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Text and Document Classification Technologies

paper · pdf · doi:10.48550/arxiv.2007.08844

openalex publication_date 2020/07/17 · openalex created_date 2020/07/23 · openalex updated_date 2026/07/28

Abstract

While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL algorithms trained under imbalanced class distributions can severely suffer when generalizing to a balanced testing criterion, since they utilize biased pseudo-labels of unlabeled data toward majority classes. To alleviate this issue, we formulate a convex optimization problem to softly refine the pseudo-labels generated from the biased model, and develop a simple algorithm, named Distribution Aligning Refinery of Pseudo-label (DARP) that solves it provably and efficiently. Under various class-imbalanced semi-supervised scenarios, we demonstrate the effectiveness of DARP and its compatibility with state-of-the-art SSL schemes.

Citations

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
• Self-training with Noisy Student improves ImageNet classification
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Sampling Control for Imbalanced Calibration in Semi-Supervised Learning
• FlexICL: A Flexible Visual In-context Learning Framework for Elbow and Wrist Ultrasound Segmentation
• Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning

Related

• An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning
• Imbalanced Semi-Supervised Learning via Label Refinement and Threshold Adjustment
• DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning
• Class-Imbalanced Semi-Supervised Learning
• On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning