Published in Arxiv, 2021
In this paper, we defend the usefulness of semantic labels but point out that fully-supervised and self-supervised methods are pursuing different kinds of features. To alleviate this issue, we present a new algorithm named Supervised Contrastive Adjustment in Neighborhood (SCAN) that maximally prevents the semantic guidance from damaging the appearance feature embedding.
Recommended citation: Longhui Wei, Lingxi Xie, Jianzhong He and etal. (2021). "Can Semantic Labels Assist Self-Supervised Visual Representation Learning?." Arxiv. https://arxiv.org/abs/2011.08621