ProcSim: Proxy-based Confidence for Robust Similarity Learning
This addresses robustness in similarity learning for applications like image retrieval, but it is incremental as it builds on existing methods for handling label noise.
The paper tackles the problem of deep metric learning being susceptible to label noise by proposing ProcSim, a framework that assigns confidence scores based on distances to class representatives, achieving state-of-the-art performance on benchmark datasets with injected noise.
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.