%0 Conference Proceedings
%T Area Under the ROC Curve Maximization for Metric Learning
%A Bojana Gajic
%A Ariel Amato
%A Ramon Baldrich
%A Joost Van de Weijer
%A Carlo Gatta
%B CVPR 2022 Workshop on Efficien Deep Learning for Computer Vision (ECV 2022, 5th Edition)
%D 2022
%F Bojana Gajic2022
%O CIC; LAMP;
%O exported from refbase (http://158.109.8.37/show.php?record=3700), last updated on Tue, 25 Apr 2023 16:00:39 +0200
%X 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.
%K Training
%K Computer vision
%K Conferences
%K Area measurement
%K Benchmark testing
%K Pattern recognition
%U http://158.109.8.37/files/GAB2022.pdf
%U http://dx.doi.org/10.1109/CVPRW56347.2022.00318