Research map / Label-efficient and robust learning / Recognition and long-tail
Adaptive Neighborhood Metric Learning
Kun Song, Junwei Han, Gong Cheng, Jiwen Lu, Feiping Nie
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 neighborhood parameters (lambda, gamma) to loss (ablation) | Lifted structure loss · CUB-200-2011 | Recall@1: 45.4 -> 47.1 | Improved |
| add neighborhood parameters (lambda, gamma) to loss (ablation) | Proxy-NCA · CUB-200-2011 | Recall@1: 49.2 -> 52.7 | Improved |
| add neighborhood parameters (lambda, gamma) to loss (ablation) | N-pairs loss · CUB-200-2011 | Recall@1: 43.6 -> 46.8 | Improved |
| add neighborhood parameters (lambda1, lambda2) (ablation) | DANML · CUB-200-2011 | Recall@1: 65.4 -> 67.6 | Improved |
| replace multi-similarity loss with DANML | Multi-similarity loss · CUB-200-2011 | Recall@1: 65.7 -> 67.6 | Improved |
| replace multi-similarity loss with DANML | Multi-similarity loss · Cars-196 | Recall@1: 84.1 -> 85.6 | Improved |
| replace Circle Loss with DANML | Circle Loss · Cars-196 | Recall@1: 83.4 -> 85.6 | Improved |
| use adaptive neighborhood instead of fixed 10-nearest-neighbor targets (LANML-) | LMNN · 15 UCI datasets | Recall@1 | Improved |
| add parameter alpha to NCA (PNCA) | NCA · 15 UCI datasets | Recall@1 | Improved |
| use ANML with a continuous log-exp mean surrogate | LMNN · running time | Recall@1 | Improved |
Closest papers by meaning
- Neighborhood-Adaptive Structure Augmented Metric Learning (AAAI 2022 · similarity 0.86)
- Smart Mining for Deep Metric Learning (ICCV 2017 · similarity 0.86)
- Hardness-Aware Deep Metric Learning (CVPR 2019 · similarity 0.85)
- Deep Metric Learning via Adaptive Learnable Assessment (CVPR 2020 · similarity 0.85)
- Denoising Multi-Similarity Formulation: A Self-Paced Curriculum-Driven Approach for Robust Metric Learning (AAAI 2023 · similarity 0.84)
- Large-Scale Distance Metric Learning With Uncertainty (CVPR 2018 · similarity 0.84)
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.
