This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples. In contrast to the standard InfoNCE loss, which requires a strict binary separation of the training pairs into similar and dissimilar samples, RINCE can exploit information about a similarity ranking for learning a corresponding embedding space. We show that the proposed loss function learns favorable embeddings compared to the standard InfoNCE whenever at least noisy ranking information can be obtained or when the definition of positives and negatives is blurry. We demonstrate this for a supervised classification task with additional superclass labels and noisy similarity scores. Furthermore, we show that RINCE can also be applied to unsupervised training with experiments on unsupervised representation learning from videos. In particular, the embedding yields higher classification accuracy, retrieval rates and performs better in out-of-distribution detection than the standard InfoNCE loss.

该论文提出了一种名为排名信息噪声对比估计(RINCE)的新的信息噪声对比损失，它可以利用相似性排名的信息来学习相应的嵌入空间，并且相比标准InfoNCE，RINCE可以通过不完全划分相似和不相似样本的情况来自适应探索相似性信息。此外，该损失函数也可以应用于无监督训练，针对视频的无监督学习，可展现出更优的分类精度、检索率和越界检测表现。

排名信息噪音对比估计：通过排名正例提高对比学习