论文标题
对抗性对比度自我监督学习
Adversarial Contrastive Self-Supervised Learning
论文作者
论文摘要
最近，从广泛的未标记数据中学习，尤其是自我监督的学习，一直在出现并引起了广泛的关注。在一些标记的示例上进行自我监督的学习，然后在一些标记的示例上进行微调，可以显着提高标签效率，并使用完全注释的数据超过标准监督培训。在这项工作中，我们基于在线硬性矿山挖掘的新颖自我监督深度学习范式。具体来说，我们设计了一个学生教师网络，以生成用于自学学习的数据的多视图，并将硬性负面对挖矿整合到培训中。然后，考虑到阳性样品对和开采的硬性样品对，我们得出了新的三胞胎样损失。广泛的实验证明了该方法在ILSVRC-2012上的有效性及其成分的有效性。
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.
