失真解耦对比学习
Distortion-Disentangled Contrastive Learning
AI总结：
针对仅正样本对对比学习未显式解耦利用失真可变表征且对增强敏感的问题，提出DDCL框架与DDL损失，提升表征效率、鲁棒性及性能。
摘要：
自监督学习以其在表征学习和各种下游计算机视觉任务中的卓越表现而闻名。最近，仅正样本对对比学习（POCL）无需构建正负样本训练集即可取得可靠性能。它通过降低对批量大小的依赖来减少内存需求。POCL方法通常使用单一损失函数来提取失真不变表征（DIR），该表征描述了受不同失真影响的正样本对表征之间的邻近性。这一损失函数隐式地使模型能够过滤或忽略受不同失真影响的失真可变表征（DVR）。然而，现有POCL方法并未显式地强制解耦和利用真正有价值的DVR。此外，已观察到这些POCL方法对增强策略较为敏感。为解决这些局限，我们提出了一个名为失真解耦对比学习（DDCL）的新型POCL框架以及一种失真解耦损失（DDL）。我们的方法首次在模型和特征流内部显式解耦并利用DVR，以提升整体表征利用效率、鲁棒性和表征能力。所开展的实验表明，在多个基准数据集上，我们的框架在收敛性、表征质量和鲁棒性方面均优于Barlow Twins和Simsiam。
英文摘要：
Self-supervised learning is well known for its remarkable performance in representation learning and various downstream computer vision tasks. Recently, Positive-pair-Only Contrastive Learning (POCL) has achieved reliable performance without the need to construct positive-negative training sets. It reduces memory requirements by lessening the dependency on the batch size. The POCL method typically uses a single loss function to extract the distortion invariant representation (DIR) which describes the proximity of positive-pair representations affected by different distortions. This loss function implicitly enables the model to filter out or ignore the distortion variant representation (DVR) affected by different distortions. However, existing POCL methods do not explicitly enforce the disentanglement and exploitation of the actually valuable DVR. In addition, these POCL methods have been observed to be sensitive to augmentation strategies. To address these limitations, we propose a novel POCL framework named Distortion-Disentangled Contrastive Learning (DDCL) and a Distortion-Disentangled Loss (DDL). Our approach is the first to explicitly disentangle and exploit the DVR inside the model and feature stream to improve the overall representation utilization efficiency, robustness and representation ability. Experiments carried out demonstrate the superiority of our framework to Barlow Twins and Simsiam in terms of convergence, representation quality, and robustness on several benchmark datasets.
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。
