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.

翻译：在多标签设置下，利用无标签且含噪声的数据学习判别性语义空间仍是一个未解决的问题。我们提出一种对比自监督学习方法，该方法对数据噪声具有鲁棒性，其理论基础源于变分方法领域。该算法（VCL）利用基于β散度的变分对比学习，能够从包括非精选和含噪声数据集在内的无标签数据中实现鲁棒学习。通过在人脸理解领域对多标签数据集进行线性评估和微调场景的严格实验，我们验证了所提方法的有效性。在几乎所有测试场景中，VCL均超越了当前最先进的自监督方法，实现了显著的准确率提升。