Contrastive learning has emerged as an essential approach for self-supervised learning in visual representation learning. The central objective of contrastive learning is to maximize the similarities between two augmented versions of an image (positive pairs), while minimizing the similarities between different images (negative pairs). Recent studies have demonstrated that harder negative samples, i.e., those that are more difficult to differentiate from the anchor sample, perform a more crucial function in contrastive learning. This paper proposes a novel feature-level method, namely sampling synthetic hard negative samples for contrastive learning (SSCL), to exploit harder negative samples more effectively. Specifically, 1) we generate more and harder negative samples by mixing negative samples, and then sample them by controlling the contrast of anchor sample with the other negative samples; 2) considering the possibility of false negative samples, we further debias the negative samples. Our proposed method improves the classification performance on different image datasets and can be readily integrated into existing methods.

翻译：对比学习已成为视觉表征学习中自监督学习的重要方法。其核心目标在于最大化同一图像两个增强版本（正样本对）之间的相似性，同时最小化不同图像（负样本对）之间的相似性。近期研究表明，更难区分的负样本（即与锚点样本差异更细微的样本）在对比学习中发挥着更关键的作用。本文提出了一种新颖的特征级方法——合成难负样本对比学习（SSCL），旨在更有效地利用难负样本。具体而言：1）我们通过混合负样本生成更多且更难的负样本，并通过控制锚点样本与其他负样本的对比度对其进行采样；2）针对潜在的错误负样本问题，我们进一步对负样本进行去偏处理。所提方法在不同图像数据集上均提升了分类性能，并能便捷地集成至现有方法中。