Research map / Label-efficient and robust learning / Recognition and long-tail
Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
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 |
|---|---|---|---|
| Add embedding expansion to Multi-Similarity loss | Multi-Similarity loss · CUB200-2011 | Recall@1 (%): 56.2 -> 57.4 | Helped |
| Add embedding expansion to Multi-Similarity loss | Multi-Similarity loss · CARS196 | Recall@1 (%): 75.0 -> 76.1 | Helped |
| Add embedding expansion to Multi-Similarity loss | Multi-Similarity loss · Stanford Online Products | Recall@1 (%): 75.9 -> 78.1 | Helped |
| Normalize the generated synthetic points with L2 normalization (ablation) | EE + triplet loss · CARS196 | Recall@1 | Helped |
| Increase synthetic points beyond the reported peak range of 2 to 8 (ablation) | EE + triplet loss with L2-normalized synthetic points · CARS196 | Recall@1 | Hurt |
| Increase synthetic point count to about 8, then maintain it at larger counts (ablation) | EE + triplet loss without L2-normalization · CARS196 | Recall@1 | Mixed |
| Omit L2 normalization on synthetic points (ablation) | EE + triplet loss · CARS196 | Recall@1 | Helped |
| Omit L2 normalization on synthetic points (ablation) | EE + triplet loss · CARS196 | training loss stability | Hurt |
Closest papers by meaning
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.87)
- Neighborhood-Adaptive Structure Augmented Metric Learning (AAAI 2022 · similarity 0.87)
- Learning Intra-Batch Connections for Deep Metric Learning (ICML 2021 · similarity 0.87)
- Deep Metric Learning via Lifted Structured Feature Embedding (CVPR 2016 · similarity 0.86)
- Symmetrical Synthesis for Deep Metric Learning (AAAI 2020 · similarity 0.86)
- Exploiting Distribution Constraints for Scalable and Efficient Image Retrieval (ICLR 2025 · 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.