Contrastive learning has become a dominant approach in self-supervised visual representation learning, with hard negatives-samples that closely resemble the anchor-being key to enhancing the discriminative power of learned representations. However, efficiently leveraging hard negatives remains a challenge due to the difficulty in identifying and incorporating them without significantly increasing computational costs. To address this, we introduce SynCo (Synthetic Negatives in Contrastive learning), a novel contrastive learning approach that improves model performance by generating synthetic hard negatives. Built on the MoCo framework, SynCo introduces six novel strategies for creating diverse synthetic hard negatives that can be generated on-the-fly with minimal computational overhead. SynCo achieves faster training and better representation learning, achieving a top-1 accuracy of 68.1% in ImageNet linear evaluation after only 200 epochs on pretraining, surpassing MoCo's 67.5% with the same ResNet-50 encoder. Additionally, it transfers more effectively to detection tasks: on the PASCAL VOC, it outperforms both the supervised baseline and MoCo, achieving an AP of 82.5%; on the COCO dataset, it sets a new benchmark with 40.4% AP for bounding box detection and 35.4% AP for instance segmentation. Our synthetic hard negative generation procedure significantly enhances the quality of visual representations learned through self-supervised contrastive learning. Code is available at https://github.com/giakoumoglou/synco.

翻译：对比学习已成为自监督视觉表征学习中的主流方法，其中困难负样本——与锚点样本高度相似的样本——对于增强所学表征的判别能力至关重要。然而，由于在不显著增加计算成本的情况下识别并有效利用困难负样本存在困难，高效利用它们仍是一个挑战。为解决此问题，我们提出了SynCo（对比学习中的合成负样本），这是一种通过生成合成困难负样本以提升模型性能的新型对比学习方法。SynCo基于MoCo框架构建，引入了六种新颖的策略来创建多样化的合成困难负样本，这些样本可以即时生成且计算开销极小。SynCo实现了更快的训练和更好的表征学习，在仅使用ResNet-50编码器进行200轮预训练后，于ImageNet线性评估中达到了68.1%的top-1准确率，超越了同等条件下MoCo的67.5%。此外，其在检测任务上表现出更优的迁移能力：在PASCAL VOC数据集上，其性能超越了有监督基线方法和MoCo，达到了82.5%的AP；在COCO数据集上，其为边界框检测设定了40.4% AP的新基准，实例分割达到了35.4% AP。我们的合成困难负样本生成过程显著提升了通过自监督对比学习获得的视觉表征质量。代码发布于https://github.com/giakoumoglou/synco。