论文标题
联合辩论的表示和图像聚类学习与自学
Joint Debiased Representation and Image Clustering Learning with Self-Supervision
论文作者
论文摘要
对比度学习是视觉表示学习最成功的方法之一，可以通过在学习的表示上共同执行聚类来进一步提高其性能。但是，现有的联合聚类和对比度学习方法在长尾数据分布上的表现不佳，因为多数班级压倒了少数群体的损失，因此可以阻止学习有意义的表示。在此激励的情况下，我们通过调整偏见的对比损失，以避免群体不平衡的少数群体类别的不平衡数据集来开发一种新颖的联合聚类和对比度学习框架。我们表明，我们提出的修改后的对比损失和差异聚类损失可改善多个数据集和学习任务的性能。源代码可从https://anonymon.4open.science/r/ssl-debiased-clustering获得
Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint clustering and contrastive learning do not perform well on long-tailed data distributions, as majority classes overwhelm and distort the loss of minority classes, thus preventing meaningful representations to be learned. Motivated by this, we develop a novel joint clustering and contrastive learning framework by adapting the debiased contrastive loss to avoid under-clustering minority classes of imbalanced datasets. We show that our proposed modified debiased contrastive loss and divergence clustering loss improves the performance across multiple datasets and learning tasks. The source code is available at https://anonymous.4open.science/r/SSL-debiased-clustering
