TY  - CONF
AU  - Bojana Gajic
AU  - Ariel Amato
AU  - Ramon Baldrich
AU  - Joost Van de Weijer
AU  - Carlo Gatta
A2  - CVPRW
PY  - 2022//
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)
KW  - Training
KW  - Computer vision
KW  - Conferences
KW  - Area measurement
KW  - Benchmark testing
KW  - Pattern recognition
N2  - 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.
L1  - http://158.109.8.37/files/GAB2022.pdf
UR  - http://dx.doi.org/10.1109/CVPRW56347.2022.00318
N1  - CIC; LAMP;
ID  - Bojana Gajic2022
ER  -