Research map / Label-efficient and robust learning / Recognition and long-tail
Neighborhood-Adaptive Structure Augmented Metric Learning
Read the paperCheck 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 |
|---|---|---|---|
| Add NASA structure embeddings to Triplet loss | Triplet metric learning · CUB | R@1: 55.5 -> 65.5 | Helped |
| Add NASA structure embeddings to Triplet loss | Triplet metric learning · Cars | R@1: 75.8 -> 85.8 | Helped |
| Add NASA structure embeddings to Triplet loss | Triplet metric learning · SOP | R@1: 72.4 -> 77.4 | Helped |
| Add NASA structure embeddings to TBH | TBH binary hashing · CIFAR-10 | MAP: 51.4 -> 52.2 | Helped |
| Add NASA structure embeddings to TBH | TBH binary hashing · NUS-WIDE | MAP: 72.5 -> 74.0 | Helped |
| Add NASA structure embeddings to TBH | TBH binary hashing · FLICKR25K | MAP: 70.1 -> 71.5 | Helped |
| Vary the loss-balance factor λ (ablation) | NASA128 + Triplet · CUB and Cars | R@1 | Mixed |
| Vary the margin factor t (ablation) | NASA128 + Triplet · CUB and Cars | R@1 | Mixed |
| Vary the embedding size (ablation) | NASA128 + Triplet · CUB | R@1 | Helped |
| Vary the embedding size (ablation) | NASA128 + Triplet · Cars | R@1 | Helped |
Closest papers by meaning
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.88)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.88)
- SLADE: A Self-Training Framework for Distance Metric Learning (CVPR 2021 · similarity 0.87)
- Local Similarity-Aware Deep Feature Embedding (NeurIPS 2016 · similarity 0.87)
- Deep Metric Learning with Self-Supervised Ranking (AAAI 2021 · similarity 0.87)
- MetricEmbedding: Accelerate Metric Nearness by Tropical Inner Product (ICML 2025 · similarity 0.85)
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.