Recently, learning from vast unlabeled data, especially self-supervised learning, has been emerging and attracted widespread attention. Self-supervised learning followed by the supervised fine-tuning on a few labeled examples can significantly improve label efficiency and outperform standard supervised training using fully annotated data. In this work, we present a novel self-supervised deep learning paradigm based on online hard negative pair mining. Specifically, we design a student-teacher network to generate multi-view of the data for self-supervised learning and integrate hard negative pair mining into the training. Then we derive a new triplet-like loss considering both positive sample pairs and mined hard negative sample pairs. Extensive experiments demonstrate the effectiveness of the proposed method and its components on ILSVRC-2012.
@article{arxiv.2202.13072,
title = {Adversarial Contrastive Self-Supervised Learning},
author = {Wentao Zhu and Hang Shang and Tingxun Lv and Chao Liao and Sen Yang and Ji Liu},
journal= {arXiv preprint arXiv:2202.13072},
year = {2022}
}