Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning with Diversity: Self-Expanded Equalization for Better Generalized Deep Metric Learning
Jiexi Yan, Zhihui Yin, Erkun Yang, Yanhua Yang, Heng Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add adaptive domain expansion (ADE) to CosFace baseline (ablation) | CosFace · CUB-200-2011 Ext. (Real -> Painting) | R@1: 31.55 -> 36.14 | Improved |
| add distribution-level equalization loss (Lde) (ablation) | SEE · CUB-200-2011 Ext. (Real -> Painting) | R@1: 38.11 -> 41.43 | Improved |
| add instance-level equalization loss (Lie) (ablation) | SEE · CUB-200-2011 Ext. (Real -> Painting) | R@1: 39.82 -> 41.43 | Improved |
| add Lde and Lie on top of ADE (ablation) | SEE · CUB-200-2011 Ext. (Real -> Water-painting) | R@1: 26.51 -> 30.52 | Improved |
| use SEE instead of proxy-based baseline | CosFace · CUB-200-2011 Ext. (Real -> Painting) | R@1: 31.55 -> 41.43 | Improved |
| use SEE instead of best baseline | Cars196 Ext. (Real -> Painting) · Cars196 Ext. (Real -> Painting) | R@1: 62.67 -> 77.25 | Improved |
| use SEE on DomainNet unseen domains | ProxyAnchor · DomainNet (average) | Recall@1: 51.13 -> 57.15 | Improved |
| test DML baselines on unseen domains | baseline DML methods · DomainNet | performance | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CosFace — CosFace: Large Margin Cosine Loss for Deep Face Recognition (CVPR 2018) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Revisiting Training Strategies and Generalization Performance in Deep Metric Learning (ICML 2020 · similarity 0.90)
- Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning (NeurIPS 2021 · similarity 0.89)
- Distance Metric Learning with Joint Representation Diversification (ICML 2020 · similarity 0.88)
- Towards Improved Proxy-Based Deep Metric Learning via Data-Augmented Domain Adaptation (AAAI 2024 · similarity 0.88)
- Deep Compositional Metric Learning (CVPR 2021 · similarity 0.88)
- Deep Disentangled Metric Learning (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
