Abstract
Deep metric learning techniques have been used for visual representation in various supervised and unsupervised learning tasks through learning embeddings of samples with deep networks. However, classic approaches, which employ a fixed distance metric as a similarity function between two embeddings, may lead to suboptimal performance for capturing the complex data distribution. The Bregman divergence generalizes measures of various distance metrics and arises throughout many fields of deep metric learning. In this paper, we first show how deep metric learning loss can arise from the Bregman divergence. We then introduce a novel method for learning empirical Bregman divergence directly from data based on parameterizing the convex function underlying the Bregman divergence with a deep learning setting. We further experimentally show that our approach performs effectively on five popular public datasets compared to other SOTA deep metric learning methods, particularly for pattern recognition problems.
| Original language | English |
|---|---|
| Title of host publication | 2023 26th International Conference on Information Fusion (FUSION) |
| Publisher | IEEE |
| ISBN (Electronic) | 979-8-89034-485-4 |
| ISBN (Print) | 979-8-3503-1320-8 |
| DOIs | |
| Publication status | Published - 2023 |
| Event | 26th International Conference on Information Fusion (FUSION 2023) - Charleston Place Hotel, Charleston, United States Duration: 27 Jun 2023 → 30 Jun 2023 https://fusion2023.org/ |
Conference
| Conference | 26th International Conference on Information Fusion (FUSION 2023) |
|---|---|
| Place | United States |
| City | Charleston |
| Period | 27/06/23 → 30/06/23 |
| Internet address |
Bibliographical note
Information for this record is supplemented by the author(s) concerned.Research Keywords
- Bregman divergence
- distance representation
- deep metric learning
- visual representation
Fingerprint
Dive into the research topics of 'Learning Empirical Bregman Divergence for Uncertain Distance Representation'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver