Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Embedding Learning With Discriminative Sampling Policy
Yueqi Duan, Lei Chen, Jiwen Lu, Jie Zhou
Check 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 |
|---|---|---|---|
| Use DE-DSP sampling instead of random sampling for triplet embedding | Triplet embedding · CUB-200-2011 | R@1: 35.9 -> 41.0 | Improved |
| Use DE-DSP sampling instead of semi-hard negative sampling for triplet embedding | Triplet embedding · Cars196 | R@1: 52.4 -> 59.3 | Improved |
| Use DE-DSP sampling instead of random sampling for triplet embedding | Triplet embedding · Stanford Online Products | R@1: 53.9 -> 58.2 | Improved |
| Use DE-DSP sampling instead of random sampling for triplet embedding | Triplet embedding · In-Shop Clothes Retrieval | R@1: 56.1 -> 58.7 | Improved |
| Use DE-DSP sampling instead of original sampling for N-pair embedding | N-pair embedding · CUB-200-2011 | R@1: 51.9 -> 53.6 | Improved |
| Use DE-DSP sampling instead of original sampling for N-pair embedding | N-pair embedding · Cars196 | R@1: 68.9 -> 72.9 | Improved |
| Use DE-DSP sampling instead of original sampling for N-pair embedding | N-pair embedding · Stanford Online Products | R@1: 66.4 -> 68.9 | Improved |
| Use DE-DSP sampling instead of original sampling for N-pair embedding | N-pair embedding · In-Shop Clothes Retrieval | R@1: 76.4 -> 78.6 | Improved |
| Use DE-DSP sampling rather than exhaustive search to select a negative sample | DE-DSP sampler · 100 classes with 100 images per class | sampling time: 4.3s -> 0.016s | Improved |
Closest papers by meaning
- Sampling Matters in Deep Embedding Learning (ICCV 2017 · similarity 0.89)
- DAS: Densely-Anchored Sampling for Deep Metric Learning (ECCV 2022 · similarity 0.86)
- Stabilizing Sample Similarity in Representation via Mitigating Random Consistency (ICML 2025 · similarity 0.85)
- $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs (ICLR 2025 · similarity 0.84)
- Towards an Explainable Comparison and Alignment of Feature Embeddings (ICML 2025 · similarity 0.83)
- Swift Sampler: Efficient Learning of Sampler by 10 Parameters (NeurIPS 2024 · similarity 0.82)
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.
