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.
翻译:采用自我监督的自我监督学习(CSL)与原型正规化(CSL)在为下游任务学习有意义的代表形式时采用了一种典型的自我监督学习(CSL),这些代表形式需要强有力的语义信息。然而,为了优化CSL(CSL),使其损失能积极执行原型正规化,例如ProtoNCE损失,可能会在嵌入空间中造成“合并”实例。也就是说,样本在原型与其它原型之间差异性差异,导致样本在原型与其它原型相分离的细小解决办法。我们根据以往的工作,建议通过协调、统一和互换(PAUC)学习原型代表性代表形式(PAUC)来缓解这一现象。具体地说,普通的ProtoNCE损失将修改为:(1) 校正原型的校正型的校正性损失;(2) 统一性损失,将原型特征统一地分配;(3) 相关损失增加原型特性的多样性和相异性差。我们根据以往的工作,在各种基准上进行了广泛的试验,结果表明我们的方法在改进原型对比性对比性对比质量结构结构之下的质量,在100-直线式调查中,通过排序之下,用直成型数据方法,用直成型数据方法,用100-直成型数据方法,用直成型数据方法进行。