论文标题
视觉表示学习的全球本地自我鉴定
Global-Local Self-Distillation for Visual Representation Learning
论文作者
论文摘要
自我监督方法的下游精度与在训练过程中解决的代理任务以及从中提取的梯度的质量紧密相关。更丰富，更有意义的梯度更新是允许自我监督的方法以更有效的方式学习的关键。在一个典型的自我验证框架中，两个增强图像的表示在全球层面是连贯的。尽管如此，将本地线索纳入代理任务可能是有益的，并提高了下游任务的模型准确性。这导致了一个双重目标，一方面，全球代表之间的一致性是强大的，另一方面，在本地代表之间的一致性被实现了。不幸的是，不存在两组本地代理之间的确切对应映射，这使得将局部代表从一个增强到另一个非平凡的任务匹配。我们建议利用输入图像中的空间信息获得几何匹配，并根据基于相似性匹配的几何方法与以前的方法进行比较。我们的研究表明，不仅1）几何匹配的表现优于低数据表格中的基于相似性的匹配，而且还有2）基于相似性的匹配在低数据方面具有高度伤害，与没有局部自我验证的香草基线相比。该代码可在https://github.com/tileb1/global-local-self-distillation上找到。
The downstream accuracy of self-supervised methods is tightly linked to the proxy task solved during training and the quality of the gradients extracted from it. Richer and more meaningful gradients updates are key to allow self-supervised methods to learn better and in a more efficient manner. In a typical self-distillation framework, the representation of two augmented images are enforced to be coherent at the global level. Nonetheless, incorporating local cues in the proxy task can be beneficial and improve the model accuracy on downstream tasks. This leads to a dual objective in which, on the one hand, coherence between global-representations is enforced and on the other, coherence between local-representations is enforced. Unfortunately, an exact correspondence mapping between two sets of local-representations does not exist making the task of matching local-representations from one augmentation to another non-trivial. We propose to leverage the spatial information in the input images to obtain geometric matchings and compare this geometric approach against previous methods based on similarity matchings. Our study shows that not only 1) geometric matchings perform better than similarity based matchings in low-data regimes but also 2) that similarity based matchings are highly hurtful in low-data regimes compared to the vanilla baseline without local self-distillation. The code is available at https://github.com/tileb1/global-local-self-distillation.
