Proxy Anchor Loss for Deep Metric Learning
CVPR, pp. 3235-3244, 2020.
We have proposed a novel metric learning loss that takes advantages of both proxy- and pair-based losses
Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity. In contrast, the latter class enables fast and reliable convergence, but cannot c...More
PPT (Upload PPT)