论文标题
通过对齐，统一性和相关性重新思考原型对比度学习
Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation
论文作者
论文摘要
在学习需要强大的语义信息的下游任务的有意义的表述中，引入了与原型正则化的对比自学学习（CSL）。但是，为了优化CSL，损失会积极地执行典型的正则化，例如，质子损失可能会导致嵌入空间中实例的“凝结”。也就是说，样品的原型内型多样性崩溃了，因为它们的原型与他人的原型构成了琐碎的解决方案。在先前的工作中，我们建议通过通过对齐，统一性和相关性学习原型表示来减轻这种现象（PAUC）。具体而言，对普通的质子损失进行了修订：（1）将嵌入正原型的嵌入在一起的比对损失在一起； （2）均匀性损失均匀地分布了典型的特征； （3）相关性损失增加了原型水平特征之间的多样性和可区分性。我们对各种基准进行了广泛的实验，其中结果证明了我们方法在提高原型对比度表示质量方面的有效性。尤其是，在使用线性探针的分类下游任务中，我们的提出方法在Imagenet-100数据集上的最新实例和原型对比度学习方法的表现优于2.96％，而Imagenet-1K数据集则在批次尺寸的相同设置下，将Imagenet-1K数据集的表现优于2.46％。
Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss that performs the prototypical regularization aggressively, e.g., the ProtoNCE loss, might cause the "coagulation" of examples in the embedding space. That is, the intra-prototype diversity of samples collapses to trivial solutions for their prototype being well-separated from others. Motivated by previous works, we propose to mitigate this phenomenon by learning Prototypical representation through Alignment, Uniformity and Correlation (PAUC). Specifically, the ordinary ProtoNCE loss is revised with: (1) an alignment loss that pulls embeddings from positive prototypes together; (2) a uniformity loss that distributes the prototypical level features uniformly; (3) a correlation loss that increases the diversity and discriminability between prototypical level features. We conduct extensive experiments on various benchmarks where the results demonstrate the effectiveness of our method in improving the quality of prototypical contrastive representations. Particularly, in the classification down-stream tasks with linear probes, our proposed method outperforms the state-of-the-art instance-wise and prototypical contrastive learning methods on the ImageNet-100 dataset by 2.96% and the ImageNet-1K dataset by 2.46% under the same settings of batch size and epochs.
