Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Metric Learning via Lifted Structured Feature Embedding
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 |
|---|---|---|---|
| Use lifted structured embedding instead of contrastive embedding | GoogLeNet · CUB-200-2011 test split | F1 | Helped |
| Use lifted structured embedding instead of triplet embedding | GoogLeNet · CUB-200-2011 test split | F1 | Helped |
| Use lifted structured embedding instead of pretrained pool5 features | GoogLeNet · CUB-200-2011 test split | F1 | Helped |
| Use lifted structured embedding instead of contrastive embedding | GoogLeNet · CARS196 test split | F1 | Helped |
| Use lifted structured embedding instead of triplet embedding | GoogLeNet · CARS196 test split | F1 | Helped |
| Use lifted structured embedding instead of pretrained pool5 features | GoogLeNet · CARS196 test split | F1 | Helped |
| Use lifted structured embedding instead of contrastive embedding | GoogLeNet · Online Products test split | Recall@K | Helped |
| Use lifted structured embedding instead of triplet embedding | GoogLeNet · Online Products test split | Recall@K | Helped |
| Replace single-hardest-negative mining with the smooth upper-bound loss (ablation) | Lifted structured embedding · Training | Convergence | Helped |
Closest papers by meaning
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.91)
- Local Similarity-Aware Deep Feature Embedding (NeurIPS 2016 · similarity 0.88)
- Deep Metric Learning via Facility Location (CVPR 2017 · similarity 0.88)
- Deep Metric Learning by Online Soft Mining and Class-Aware Attention (AAAI 2019 · similarity 0.88)
- Ranked List Loss for Deep Metric Learning (CVPR 2019 · similarity 0.88)
- Learning Intra-Batch Connections for Deep Metric Learning (ICML 2021 · similarity 0.88)
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.