PT Unknown
AU Bojana Gajic
   Ariel Amato
   Ramon Baldrich
   Joost Van de Weijer
   Carlo Gatta
TI Area Under the ROC Curve Maximization for Metric Learning
BT CVPR 2022 Workshop on Efficien Deep Learning for Computer Vision (ECV 2022, 5th Edition)
PY 2022
DI 10.1109/CVPRW56347.2022.00318
DE Training; Computer vision; Conferences; Area measurement; Benchmark testing; Pattern recognition
AB Most popular metric learning losses have no direct relation with the evaluation metrics that are subsequently applied to evaluate their performance. We hypothesize that training a metric learning model by maximizing the area under the ROC curve (which is a typical performance measure of recognition systems) can induce an implicit ranking suitable for retrieval problems. This hypothesis is supported by previous work that proved that a curve dominates in ROC space if and only if it dominates in Precision-Recall space. To test this hypothesis, we design and maximize an approximated, derivable relaxation of the area under the ROC curve. The proposed AUC loss achieves state-of-the-art results on two large scale retrieval benchmark datasets (Stanford Online Products and DeepFashion In-Shop). Moreover, the AUC loss achieves comparable performance to more complex, domain specific, state-of-the-art methods for vehicle re-identification.
ER