Threshold-Consistent Margin Loss for Open-World Deep Metric Learning ...
Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions. When combined with the common practice of using a fixed threshold to declare a match, this gives r...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | unknown |
| Published: |
arXiv
2023
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.48550/arxiv.2307.04047 https://arxiv.org/abs/2307.04047 |
| Summary: | Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions. When combined with the common practice of using a fixed threshold to declare a match, this gives rise to significant performance variations in terms of false accept rate (FAR) and false reject rate (FRR) across test classes and data distributions. We define this issue in DML as threshold inconsistency. In real-world applications, such inconsistency often complicates the threshold selection process when deploying commercial image retrieval systems. To measure this inconsistency, we propose a novel variance-based metric called Operating-Point-Inconsistency-Score (OPIS) that quantifies the variance in the operating characteristics across classes. Using the OPIS metric, we find that achieving high accuracy levels in a DML model does not automatically guarantee threshold consistency. In fact, our investigation ... : Accepted to ICLR'24 ... |
|---|