On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning

TL;DR

This paper analyzes the impact of out-of-distribution data on pseudo-labeling in class-mismatched semi-supervised learning and proposes methods to improve performance by re-balancing labels and exploring semantic clusters.

Contribution

It identifies the imbalance issue caused by OOD data in pseudo-labeling and introduces RPL and SEC to mitigate this problem and enhance SSL performance.

Findings

RPL filters out OOD data and balances pseudo-labels.

SEC creates pseudo-labels for extra classes via clustering.

Proposed methods outperform baselines across benchmarks.

Abstract

When there are unlabeled Out-Of-Distribution (OOD) data from other classes, Semi-Supervised Learning (SSL) methods suffer from severe performance degradation and even get worse than merely training on labeled data. In this paper, we empirically analyze Pseudo-Labeling (PL) in class-mismatched SSL. PL is a simple and representative SSL method that transforms SSL problems into supervised learning by creating pseudo-labels for unlabeled data according to the model's prediction. We aim to answer two main questions: (1) How do OOD data influence PL? (2) What is the proper usage of OOD data with PL? First, we show that the major problem of PL is imbalanced pseudo-labels on OOD data. Second, we find that OOD data can help classify In-Distribution (ID) data given their OOD ground truth labels. Based on the findings, we propose to improve PL in class-mismatched SSL with two components -- Re-balanced Pseudo-Labeling (RPL) and Semantic Exploration Clustering (SEC). RPL re-balances pseudo-labels of high-confidence data, which simultaneously filters out OOD data and addresses the imbalance problem. SEC uses balanced clustering on low-confidence data to create pseudo-labels on extra classes, simulating the process of training with ground truth. Experiments show that our method achieves steady improvement over supervised baseline and state-of-the-art performance under all class mismatch ratios on different benchmarks.