RankMe：通过秩评估预训练自监督表示的下游性能
RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank
AI总结：
本研究提出了RankMe，一种基于有效秩的无监督评估标准，无需标签即可准确评估JE-SSL表示的下游性能并选择超参数，且不增加计算负担。
摘要：
联合嵌入自监督学习（JE-SSL）经历了快速发展，出现了许多方法变体，但几乎没有原则性指南能帮助从业者成功部署它们。导致这一陷阱的主要原因在于，JE-SSL的核心原则是不采用任何输入重建，因此缺乏训练不成功的视觉线索。再加上缺乏信息量的损失值，在无法借助标签来评判所学习表示质量的新数据集上部署SSL变得十分困难。在本研究中，我们开发了一种简单的无监督标准，用以指示所学习的JE-SSL表示的质量：它们的有效秩（effective rank）。尽管简单且计算友好，这种被称为RankMe的方法允许人们在不同下游数据集上评估JE-SSL表示的性能，而无需任何标签。RankMe的另一个好处是它没有任何需要调整的训练或超参数。通过涉及数百次训练 episodes 的详尽经验实验，我们展示了如何将RankMe用于超参数选择，且与涉及数据集标签的当前选择方法相比，最终性能几乎没有降低。我们希望RankMe能促进JE-SSL在无法依赖标签进行表示质量评估的领域中的部署。
英文摘要：
Joint-Embedding Self Supervised Learning (JE-SSL) has seen a rapid development, with the emergence of many method variations but only few principled guidelines that would help practitioners to successfully deploy them. The main reason for that pitfall comes from JE-SSL's core principle of not employing any input reconstruction therefore lacking visual cues of unsuccessful training. Adding non informative loss values to that, it becomes difficult to deploy SSL on a new dataset for which no labels can help to judge the quality of the learned representation. In this study, we develop a simple unsupervised criterion that is indicative of the quality of the learned JE-SSL representations: their effective rank. Albeit simple and computationally friendly, this method -- coined RankMe -- allows one to assess the performance of JE-SSL representations, even on different downstream datasets, without requiring any labels. A further benefit of RankMe is that it does not have any training or hyper-parameters to tune. Through thorough empirical experiments involving hundreds of training episodes, we demonstrate how RankMe can be used for hyperparameter selection with nearly no reduction in final performance compared to the current selection method that involve a dataset's labels. We hope that RankMe will facilitate the deployment of JE-SSL towards domains that do not have the opportunity to rely on labels for representations' quality assessment.
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。
