Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Metric Learning via Adaptive Learnable Assessment
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace fixed triplet sampling with adaptive learnable assessment | Triplet metric learning · CUB-200-2011 | R@1: 35.9 -> 46.3 | Helped |
| use disjoint-label training and validation subsets instead of random tuples (ablation) | ALA with triplet loss · CUB-200-2011 | R@1: 44.4 -> 46.3 | Helped |
| add adaptive learnable assessment to triplet loss (ablation) | Triplet metric learning · Cars196 | R@1: 45.1 -> 67.2 | Helped |
| add adaptive learnable assessment to margin loss (ablation) | Margin metric learning · CUB-200-2011 | R@1: 49.6 -> 61.6 | Helped |
| add adaptive learnable assessment to contrastive loss (ablation) | Contrastive metric learning · CUB-200-2011 | R@1: 27.2 -> 37.3 | Helped |
| add adaptive learnable assessment to triplet loss (ablation) | Triplet metric learning · Stanford Online Products | R@1: 53.9 -> 68.6 | Helped |
| use adaptive learnable assessment on the large Stanford Online Products dataset | Deep metric learning · Stanford Online Products | R@1: 66.5 -> 68.6 | Helped |
Closest papers by meaning
- Revisiting Training Strategies and Generalization Performance in Deep Metric Learning (ICML 2020 · similarity 0.88)
- Deep Factorized Metric Learning (CVPR 2023 · similarity 0.87)
- Towards Improved Proxy-Based Deep Metric Learning via Data-Augmented Domain Adaptation (AAAI 2024 · similarity 0.86)
- Deep Metric Learning Beyond Binary Supervision (CVPR 2019 · similarity 0.86)
- Deep Compositional Metric Learning (CVPR 2021 · similarity 0.86)
- Deep Metric Learning to Rank (CVPR 2019 · similarity 0.86)
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.