Research map / Label-efficient and robust learning / Recognition and long-tail
Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings
Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein
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 |
|---|---|---|---|
| add HORDE regularizer | contrastive loss (GoogleNet) · CUB-200-2011 | Recall@1 (%): 55.0 -> 57.1 | Improved |
| add HORDE regularizer | contrastive loss (GoogleNet) · Cars-196 | Recall@1 (%): 72.2 -> 76.2 | Improved |
| add HORDE regularizer | Triplet loss (GoogleNet) · CUB-200-2011 | Recall@1 (%): 50.5 -> 53.6 | Improved |
| add HORDE regularizer | Triplet loss (GoogleNet) · Cars-196 | Recall@1 (%): 65.2 -> 74.0 | Improved |
| add HORDE regularizer | Binomial Deviance (GoogleNet) · CUB-200-2011 | Recall@1 (%): 55.9 -> 58.3 | Improved |
| add HORDE regularizer | Binomial Deviance (GoogleNet) · Cars-196 | Recall@1 (%): 78.2 -> 81.5 | Improved |
| add HORDE regularizer | Binomial Deviance (GoogleNet) · Stanford Online Products | Recall@1 (%): 67.4 -> 72.6 | Improved |
| add HORDE regularizer | Binomial Deviance (GoogleNet) · In-Shop Clothes Retrieval | Recall@1 (%): 81.3 -> 84.4 | Improved |
| add HORDE regularizer | ABE ensemble (GoogleNet) · CUB-200-2011 | Recall@1 (%): 60.0 -> 62.7 | Improved |
| add HORDE regularizer | ABE ensemble (GoogleNet) · Cars-196 | Recall@1 (%): 79.2 -> 86.4 | Improved |
| use all concatenated high-order moments at test time (PCA to 512) (ablation) | Binomial Deviance + HORDE · CUB-200-2011 | Recall@1 (%): 58.3 -> 59.4 | Improved |
| use all concatenated high-order moments at test time (PCA to 512) (ablation) | Binomial Deviance + HORDE · Cars-196 | Recall@1 (%): 81.5 -> 83.2 | Improved |
Closest papers by meaning
- Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering (AAAI 2019 · similarity 0.87)
- Improving Deep Metric Learning by Divide and Conquer (TPAMI 2021 · similarity 0.87)
- Multi-level Distance Regularization for Deep Metric Learning (AAAI 2021 · similarity 0.86)
- Revisiting Training Strategies and Generalization Performance in Deep Metric Learning (ICML 2020 · similarity 0.86)
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.86)
- DIML: Deep Interpretable Metric Learning via Structural Matching (TPAMI 2023 · similarity 0.86)
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.
