Publication
Procsim: Proxy-based confidence for robust similarity learning
Conference Article
Conference
IEEE Winter Conference on Applications of Computer Vision (WACV)
Edition
2024
Pages
1297-1306
Doc link
https://doi.org/10.1109/WACV57701.2024.00134
File
Abstract
Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain numerous wrong labels, and DML methods are susceptible to them. Intending to study the effect of realistic noise, we create an ontology of the classes in a dataset and use it to simulate semantically coherent labeling mistakes. To train robust DML models, we propose ProcSim, a simple framework that assigns a confidence score to each sample using the normalized distance to its class representative. The experimental results show that the proposed method achieves state-of-the-art performance on the DML benchmark datasets injected with uniform and the proposed semantically coherent noise.
Categories
computer vision.
Author keywords
robustness,deep metric learning,contrastive learning
Scientific reference
O. Barbany, X. Lin, M. Bastan and A. Dhua. Procsim: Proxy-based confidence for robust similarity learning, 2024 IEEE Winter Conference on Applications of Computer Vision, 2024, Waikoloa, Hawaii, pp. 1297-1306.
Follow us!