使用 Beta 散度的变分自监督对比学习
Variational Self-Supervised Contrastive Learning Using Beta Divergence
AI总结：
针对多标签场景下未标注含噪数据的判别表示学习问题，提出结合 beta 散度的变分对比自监督方法 VCL，并在人脸理解多标签实验中取得优于现有自监督方法的准确率。
摘要：
在多标签设置中，利用未标注且含噪的数据学习具有判别性的语义空间仍是一个尚未解决的问题。本文提出一种对数据噪声具有鲁棒性的对比自监督学习方法，其理论基础位于变分方法领域。该方法（VCL）利用结合 beta 散度的变分对比学习，从包括未经筛选和含噪数据集在内的未标注数据集中进行鲁棒学习。通过在人脸理解领域使用多标签数据集开展严格实验，包括线性评估和微调场景，本文证明了所提方法的有效性。在几乎所有测试场景中，VCL 均超越最先进自监督方法的性能，实现了显著的准确率提升。
英文摘要：
Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of variational methods. The method (VCL) utilizes variational contrastive learning with beta-divergence to learn robustly from unlabelled datasets, including uncurated and noisy datasets. We demonstrate the effectiveness of the proposed method through rigorous experiments including linear evaluation and fine-tuning scenarios with multi-label datasets in the face understanding domain. In almost all tested scenarios, VCL surpasses the performance of state-of-the-art self-supervised methods, achieving a noteworthy increase in accuracy.
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。
