SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples

TL;DR

SeMi introduces a novel approach for imbalanced semi-supervised learning by mining hard examples and maintaining a class-balanced memory bank, significantly improving performance on standard benchmarks.

Contribution

The paper proposes a simple yet effective method that leverages hard example mining and confidence decay to enhance imbalanced semi-supervised learning.

Findings

Outperforms state-of-the-art methods on multiple benchmarks

Achieves approximately 54.8% improvement in reversed scenarios

Effectively addresses class imbalance and hard example utilization

Abstract

Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation. Existing class-imbalanced semi-supervised learning (CISSL) methods mainly focus on rebalancing datasets but ignore the potential of using hard examples to enhance performance, making it difficult to fully harness the power of unlabeled data even with sophisticated algorithms. To address this issue, we propose a method that enhances the performance of Imbalanced Semi-Supervised Learning by Mining Hard Examples (SeMi). This method distinguishes the entropy differences among logits of hard and easy examples, thereby identifying hard examples and increasing the utility of unlabeled data, better addressing the imbalance problem in CISSL. In addition, we maintain a class-balanced memory bank with confidence decay for storing high-confidence embeddings to enhance the pseudo-labels' reliability. Although our method is simple, it is effective and seamlessly integrates with existing approaches. We perform comprehensive experiments on standard CISSL benchmarks and experimentally demonstrate that our proposed SeMi outperforms existing state-of-the-art methods on multiple benchmarks, especially in reversed scenarios, where our best result shows approximately a 54.8\% improvement over the baseline methods.