In this paper, we propose a novel co-learning framework (CoSSL) with decoupled representation learning and classifier learning for imbalanced SSL. To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE) for classifier learning. Furthermore, the current evaluation protocol for imbalanced SSL focuses only on balanced test sets, which has limited practicality in real-world scenarios. Therefore, we further conduct a comprehensive evaluation under various shifted test distributions. In experiments, we show that our approach outperforms other methods over a large range of shifted distributions, achieving state-of-the-art performance on benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our code will be made publicly available.

翻译：在本文中,我们提出一个新的共同学习框架(COSSL),为不平衡的SSL提供分解的代表性学习和分类学习。为了处理数据不平衡问题,我们设计了用于分类学习的尾级地物增强(TFE),此外,目前对不平衡的SSL的评价程序只侧重于平衡的测试组,在现实世界情景中,这种测试组的实用性有限。因此,我们进一步在各种转移式的测试分布下进行全面评估。在实验中,我们显示我们的方法优于其他方法,超越了广泛的转移式分布,在从CIFAR-10、CIFAR-100、图像网到Food-101等基准数据集上取得最先进的性能。我们的代码将公布于众。