Deep metric learning to rank
Files
Accepted manuscript
Date
2019-06
Authors
Cakir, Fatih
He, Kun
Xia, Xide
Kulis, Brian
Sclaroff, Stan
Version
Accepted manuscript
OA Version
Citation
Fatih Cakir, Kun He, Xide Xia, Brian Kulis, Stan Sclaroff. 2019. "Deep Metric Learning to Rank." 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019-06-15 - 2019-06-20. https://doi.org/10.1109/cvpr.2019.00196
Abstract
We propose a novel deep metric learning method by revisiting the learning to rank approach. Our method, named FastAP, optimizes the rank-based Average Precision measure, using an approximation derived from distance quantization. FastAP has a low complexity compared to existing methods, and is tailored for stochastic gradient descent. To fully exploit the benefits of the ranking formulation, we also propose a new minibatch sampling scheme, as well as a simple heuristic to enable large-batch training. On three few-shot image retrieval datasets, FastAP consistently outperforms competing methods, which often involve complex optimization heuristics or costly model ensembles.