MNN: Mixed Nearest-Neighbors for Self-Supervised Learning
This work addresses a specific challenge in self-supervised learning for computer vision, representing an incremental improvement.
The paper tackles the problem of false neighbors in self-supervised learning by introducing MNN, a framework that uses weighting and image mixture to optimize neighbor influence, resulting in exceptional generalization and training efficiency on four benchmark datasets.
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.