In contrastive self-supervised learning, positive samples are typically drawn from the same image but in different augmented views, resulting in a relatively limited source of positive samples. An effective way to alleviate this problem is to incorporate the relationship between samples, which involves including the top-K nearest neighbors of positive samples. However, the problem of false neighbors (i.e., neighbors that do not belong to the same category as the positive sample) is an objective but often overlooked challenge due to the query of neighbor samples without supervision information. In this paper, we present a simple self-supervised learning framework called Mixed Nearest-Neighbors for Self-Supervised Learning (MNN). MNN optimizes the influence of neighbor samples on the semantics of positive samples through an intuitive weighting approach and image mixture operations. The results demonstrate that MNN exhibits exceptional generalization performance and training efficiency on four benchmark datasets.

翻译：在对比自监督学习中，正样本通常来自同一图像的不同增强视图，导致正样本来源相对有限。缓解该问题的有效途径是引入样本间关系，即纳入正样本的前K个最近邻。然而，由于缺乏监督信息进行邻域样本查询，假邻居（即与正样本不属于同一类别的邻居）问题成为一个客观存在但常被忽视的挑战。本文提出一种名为"面向自监督学习的混合最近邻方法"（MNN）的简单自监督学习框架。MNN通过直观的加权策略与图像混合操作，优化邻域样本对正样本语义的影响。实验结果表明，MNN在四个基准数据集上展现出卓越的泛化性能与训练效率。