Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Improved and Interpretable Deep Metric Learning via Attentive Grouping
Xinyi Xu, Zhengyang Wang, Cheng Dan Deng, Hao Yuan, Shuiwang Ji
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 A-grouping (4x128) instead of no grouping (ablation) | ResNet-50 + Margin · Cars-196 | Recall@1: 79.92 -> 87.06 | Improved |
| add A-grouping (4x128) instead of no grouping (ablation) | ResNet-50 + Margin · CUB-200-2011 | Recall@1: 63.09 -> 68.62 | Improved |
| add A-grouping (4x128) instead of no grouping (ablation) | Inception-v1 + Binomial · Cars-196 | Recall@1: 71.70 -> 80.00 | Improved |
| add A-grouping (4x128) instead of no grouping (ablation) | Inception-v1 + Margin · Cars-196 | Recall@1: 73.12 -> 80.23 | Improved |
| add A-grouping (4x128) instead of no grouping (ablation) | Inception-v1 + Contrastive · CUB-200-2011 | Recall@1: 54.74 -> 57.06 | Improved |
| add A-grouping (4x128) instead of no grouping (ablation) | ResNet-50 + Binomial · Cars-196 | Recall@1: 80.90 -> 85.70 | Improved |
| add A-grouping (4x128) instead of no grouping (ablation) | ResNet-50 + Margin · SOP | Recall@1: 78.32 -> 78.70 | No clear effect |
| use A-grouping instead of channel grouping (ablation) | ResNet-50 + Margin · Cars-196 | Recall@1: 84.93 -> 87.06 | Improved |
| use A-grouping instead of channel grouping (ablation) | Inception-v1 + Contrastive · Cars-196 | Recall@1: 71.84 -> 71.34 | Hurt |
| use A-grouping instead of channel grouping (ablation) | ResNet-50 + Margin · SOP | Recall@1: 77.66 -> 78.70 | Improved |
| use gate grouping instead of A-grouping (ablation) | ResNet-50 + Margin · SOP | Recall@1: 78.70 -> 76.58 | Hurt |
| use multi-linear grouping instead of A-grouping (ablation) | ResNet-50 + Binomial · Cars-196 | Recall@1: 85.70 -> 82.33 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DiVA — DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning (ECCV 2020) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Attention-based Ensemble for Deep Metric Learning (ECCV 2018 · similarity 0.87)
- The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning (TPAMI 2022 · similarity 0.87)
- Improving Deep Metric Learning by Divide and Conquer (TPAMI 2021 · similarity 0.86)
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.86)
- Attentive Group Equivariant Convolutional Networks (ICML 2020 · similarity 0.86)
- Sharing Matters for Generalization in Deep Metric Learning (TPAMI 2020 · 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.
