We propose Guided Positive Sampling Self-Supervised Learning (GPS-SSL), a general method to inject a priori knowledge into Self-Supervised Learning (SSL) positive samples selection. Current SSL methods leverage Data-Augmentations (DA) for generating positive samples and incorporate prior knowledge - an incorrect, or too weak DA will drastically reduce the quality of the learned representation. GPS-SSL proposes instead to design a metric space where Euclidean distances become a meaningful proxy for semantic relationship. In that space, it is now possible to generate positive samples from nearest neighbor sampling. Any prior knowledge can now be embedded into that metric space independently from the employed DA. From its simplicity, GPS-SSL is applicable to any SSL method, e.g. SimCLR or BYOL. A key benefit of GPS-SSL is in reducing the pressure in tailoring strong DAs. For example GPS-SSL reaches 85.58% on Cifar10 with weak DA while the baseline only reaches 37.51%. We therefore move a step forward towards the goal of making SSL less reliant on DA. We also show that even when using strong DAs, GPS-SSL outperforms the baselines on under-studied domains. We evaluate GPS-SSL along with multiple baseline SSL methods on numerous downstream datasets from different domains when the models use strong or minimal data augmentations. We hope that GPS-SSL will open new avenues in studying how to inject a priori knowledge into SSL in a principled manner.

翻译：我们提出引导正采样自监督学习（GPS-SSL），这是一种将先验知识注入自监督学习（SSL）正样本选取的通用方法。现有SSL方法依赖数据增强（DA）生成正样本，但若先验知识不准确或DA强度过弱，将显著降低所学表征的质量。GPS-SSL提出构建一个度量空间，其中欧氏距离成为语义关系的有效代理。在该空间中，可通过最近邻采样生成正样本，且任何先验知识均可独立于所使用的DA嵌入该度量空间。凭借其简洁性，GPS-SSL可应用于任何SSL方法（如SimCLR或BYOL）。GPS-SSL的关键优势在于减轻了对定制强DA的依赖。例如，使用弱DA时，GPS-SSL在Cifar10上达到85.58%的准确率，而基线方法仅达37.51%。这使我们向降低SSL对DA依赖性的目标迈进一步。我们还证明，即使采用强DA，GPS-SSL在尚未充分研究的领域仍优于基线方法。我们在不同领域的多个下游数据集上，对采用强或最小数据增强的模型进行了GPS-SSL与多种基线SSL方法的评估。希望GPS-SSL为研究如何以原则性方式将先验知识注入SSL开辟新途径。