贝叶斯自监督对比学习
Bayesian Self-Supervised Contrastive Learning
AI总结：
针对自监督对比学习中随机负样本易出现假负例导致训练偏差的问题，提出BCL损失，在贝叶斯框架下设计带位置与浓度参数的参数化采样分布，用重要性权重修正偏差并挖掘难负例，实验验证了其有效性与优越性。
摘要：
近年来，对比学习在众多领域取得了诸多成功应用，但其自监督版本仍存在许多值得探索的挑战。由于负样本从无标签数据集中抽取，随机选取的样本对于锚点而言实际上可能是假负例，会导致编码器训练出错。本文提出了一种名为BCL损失的新型自监督对比损失，该损失仍使用从无标签数据中随机抽取的样本，同时通过重要性权重修正由此产生的偏差。其核心思路是在贝叶斯框架下，为挖掘难例真负样本设计理想的采样分布。该方法的突出优势在于理想采样分布是一种参数化结构，分别设有用于修正假负例偏差的位置参数，以及用于挖掘难负例的浓度参数。实验验证了BCL损失的有效性与优越性。
英文摘要：
Recent years have witnessed many successful applications of contrastive learning in diverse domains, yet its self-supervised version still remains many exciting challenges. As the negative samples are drawn from unlabeled datasets, a randomly selected sample may be actually a false negative to an anchor, leading to incorrect encoder training. This paper proposes a new self-supervised contrastive loss called the BCL loss that still uses random samples from the unlabeled data while correcting the resulting bias with importance weights. The key idea is to design the desired sampling distribution for sampling hard true negative samples under the Bayesian framework. The prominent advantage lies in that the desired sampling distribution is a parametric structure, with a location parameter for debiasing false negative and concentration parameter for mining hard negative, respectively. Experiments validate the effectiveness and superiority of the BCL loss.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
