Research map / Graph learning / Graph algorithms and clustering
Deep Metric Learning with Graph Consistency
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 graph consistency regularization to Triplet | Triplet · CARS | Recall@1: 68.1 -> 75.8 | Helped |
| Add graph consistency regularization to N-Pair | N-Pair · CARS | Recall@1: 74.4 -> 75.8 | Helped |
| Add graph consistency regularization to Binomial | Binomial · CARS | Recall@1: 73.1 -> 79.3 | Helped |
| Add graph consistency regularization to Triplet | Triplet · Stanford Online Products | Recall@1: 57.6 -> 64.1 | Helped |
| Add graph consistency regularization to N-Pair | N-Pair · Stanford Online Products | Recall@1: 67.8 -> 68.4 | Helped |
| Add graph consistency regularization to Binomial | Binomial · Stanford Online Products | Recall@1: 68.2 -> 70.8 | Helped |
| Add graph consistency regularization to Triplet | Triplet · CUB | Recall@1: 49.4 -> 53.3 | Helped |
| Add graph consistency regularization to N-Pair | N-Pair · CUB | Recall@1: 50.5 -> 52.1 | Helped |
| Add graph consistency regularization to Binomial | Binomial · CUB | Recall@1: 52.5 -> 54.8 | Helped |
| Add graph consistency regularization to Triplet | Triplet · In-Shop | Recall@1: 63.8 -> 67.5 | Helped |
| Add graph consistency regularization to N-Pair | N-Pair · In-Shop | Recall@1: 78.3 -> 78.9 | Helped |
| Add graph consistency regularization to Binomial | Binomial · In-Shop | Recall@1: 81.8 -> 82.6 | Helped |
Closest papers by meaning
- Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies (NeurIPS 2020 · similarity 0.88)
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.88)
- Not All Classes Stand on Same Embeddings: Calibrating a Semantic Distance with Metric Tensor (CVPR 2024 · similarity 0.87)
- Threshold-Consistent Margin Loss for Open-World Deep Metric Learning (ICLR 2024 · similarity 0.86)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.85)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · 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.