Exploring a substantial amount of unlabeled data, semi-supervised learning (SSL) boosts the recognition performance when only a limited number of labels are provided. However, traditional methods assume that the data distribution is class-balanced, which is difficult to achieve in reality due to the long-tailed nature of real-world data. While the data imbalance problem has been extensively studied in supervised learning (SL) paradigms, directly transferring existing approaches to SSL is nontrivial, as prior knowledge about data distribution remains unknown in SSL. In light of this, we propose Balanced Memory Bank (BMB), a semi-supervised framework for long-tailed recognition. The core of BMB is an online-updated memory bank that caches historical features with their corresponding pseudo labels, and the memory is also carefully maintained to ensure the data therein are class-rebalanced. Additionally, an adaptive weighting module is introduced to work jointly with the memory bank so as to further re-calibrate the biased training process. We conduct experiments on multiple datasets and demonstrate, among other things, that BMB surpasses state-of-the-art approaches by clear margins, for example 8.2$\%$ on the 1$\%$ labeled subset of ImageNet127 (with a resolution of 64$\times$64) and 4.3$\%$ on the 50$\%$ labeled subset of ImageNet-LT.

翻译：半监督学习通过利用大量未标注数据，能在仅提供少量标签时提升识别性能。然而，传统方法假设数据分布是类别平衡的，这在实际中因现实数据的长尾特性而难以实现。虽然数据不平衡问题已在监督学习范式中得到广泛研究，但将现有方法直接迁移至半监督学习并非易事，因为半监督学习中数据分布的先验知识仍属未知。鉴于此，我们提出平衡记忆库——一种用于长尾识别的半监督框架。BMB的核心是一个在线更新的记忆库，用于缓存带有对应伪标签的历史特征，并通过精心维护确保其中数据的类别再平衡。此外，引入自适应加权模块与记忆库协同工作，以进一步校正有偏的训练过程。我们在多个数据集上进行实验，结果表明BMB以显著优势超越现有最优方法，例如在ImageNet127的1%标注子集（分辨率为64×64）上提升8.2%，在ImageNet-LT的50%标注子集上提升4.3%。