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

by   Jaehyung Kim, et al.

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.


page 1

page 2

page 3

page 4


ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning

Existing semi-supervised learning (SSL) algorithms typically assume clas...

Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning

The capability of the traditional semi-supervised learning (SSL) methods...

Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning

Semi-Supervised Learning (SSL) has shown its strong ability in utilizing...

AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning

Semi-supervised learning (SSL) has recently proven to be an effective pa...

On Non-Random Missing Labels in Semi-Supervised Learning

Semi-Supervised Learning (SSL) is fundamentally a missing label problem,...

BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets

Current semi-supervised learning (SSL) methods assume a balance between ...

Transfer and Share: Semi-Supervised Learning from Long-Tailed Data

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-im...