ProcSim: Proxy-based Confidence for Robust Similarity Learning ...

• Main Authors: Barbany, Oriol, Lin, Xiaofan, Bastan, Muhammet, Dhua, Arnab
• Format: Report
• Language: unknown
• Published: arXiv 2023
• Subjects: Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences; DML
• Online Access: https://dx.doi.org/10.48550/arxiv.2311.00668; https://arxiv.org/abs/2311.00668

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. ... : Accepted to the algorithms track of WACV 2024 ...