Research map / Detection and segmentation / Open-set and few-shot detection
What Makes Objects Similar: A Unified Multi-Metric Learning Approach
Han-Jia Ye, De-Chuan Zhan, Xue-Min Si, Yuan Jiang, Zhi-Hua Zhou
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 |
|---|---|---|---|
| UM2L-ADS multi-metric vs EGO on Facebook circles | UM2L (ADS) · Facebook_348 | BER: .426 -> .405 | Improved |
| UM2L-ADS vs EGO | UM2L (ADS) · Facebook_698 | BER: .392 -> .420 | Hurt |
| UM2L-ADS vs EGO on Facebook_3980 | UM2L (ADS) · Facebook_3980 | BER: .538 -> .402 | Improved |
| UM2L-ADS vs SCA on synthetic feature pattern discovery | UM2L (ADS) · ccd | BER: .250 -> .071 | Improved |
| UM2L-ADS vs SCA on reuters | UM2L (ADS) · reuters | BER: .400 -> .398 | No clear effect |
| UM2L-ADS vs ITML/LMNN etc. over 10 UCI sets | UM2L (ADS) · 10 benchmark datasets, 3NN | W/T/L: 8 / 2 / 0 vs EUCLID | Improved |
| RGS vs ADS configuration of UM2L | UM2L (RGS) · 10 benchmark datasets, 3NN | W/T/L vs ISD: 7 / 3 / 0 -> 9 / 1 / 0 | Improved |
| RGS instead of ADS | UM2L · Glass | 3NN test error: .312 -> .293 | Improved |
| RGS instead of ADS | UM2L · Autompg | 3NN test error: .201 -> .225 | Hurt |
| UM2L-ADS vs PLML | UM2L (ADS) · Hayes-r | 3NN test error: .436 -> .276 | Improved |
| UM2L-ADS vs MMLMNN | UM2L (ADS) · Autompg | 3NN test error: .256 -> .201 | Improved |
| UM2L-ADS vs MMLMNN on Glass | UM2L (ADS) · Glass | 3NN test error: .296 -> .312 | Hurt |
Closest papers by meaning
- Learning Multiple Local Metrics: Global Consideration Helps (TPAMI 2019 · similarity 0.86)
- Integrating Language Guidance Into Vision-Based Deep Metric Learning (CVPR 2022 · similarity 0.85)
- DIML: Deep Interpretable Metric Learning via Structural Matching (TPAMI 2023 · similarity 0.84)
- VisMin: Visual Minimal-Change Understanding (NeurIPS 2024 · similarity 0.84)
- Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding (CVPR 2024 · similarity 0.84)
- Volume-Aware Distance for Robust Similarity Learning (ICML 2025 · similarity 0.83)
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.
