Research map / Label-efficient and robust learning / Knowledge distillation
Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations
Wenjie Pei, Shuang Wu, Dianwen Mei, Fanglin Chen, Jiandong Tian, Guangming Lu
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 BoVW knowledge distillation | TFA++ · PASCAL VOC Novel Split 1 (2-shot) | nAP50: 42.1 -> 50.2 | Improved |
| add BoVW knowledge distillation | TFA++ · PASCAL VOC Novel Split 1 (10-shot) | nAP50: 60.8 -> 64.2 | Improved |
| add BoVW knowledge distillation | DeFRCN · PASCAL VOC Novel Split 1 (2-shot) | nAP50: 58.6 -> 62.5 | Improved |
| add BoVW knowledge distillation | DeFRCN · PASCAL VOC Novel Split 3 (10-shot) | nAP50: 62.5 -> 62.2 | No clear effect |
| add BoVW knowledge distillation | DeFRCN · MS COCO (30-shot) | nAP: 22.5 -> 22.6 | No clear effect |
| add BoVW knowledge distillation | TFA++ · MS COCO (10-shot) | nAP: 11.7 -> 12.8 | Improved |
| train with only 10% of base data, add BoVW distillation | DeFRCN · MS COCO 10% base data (30-shot) | nAP: 14.9 -> 16.0 | Improved |
| add base-class distillation (ablation) | TFA++ · PASCAL VOC Novel Split 1 (3-shot) | nAP50: 47.3 -> 51.5 | Improved |
| add novel-class distillation (ablation) | TFA++ · PASCAL VOC Novel Split 1 (5-shot) | nAP50: 59.7 -> 60.6 | Improved |
| add score fusion of original and BoVW classification (ablation) | TFA++ · PASCAL VOC Novel Split 1 (5-shot) | nAP50: 60.6 -> 62.1 | Improved |
| add DeCov loss (ablation) | TFA++ · PASCAL VOC Novel Split 1 (10-shot) | nAP50: 61.3 -> 63.1 | Improved |
| distill on BoVW representations instead of deep features (ablation) | TFA++ · PASCAL VOC Novel Split 1 (10-shot) | nAP50: 48.3 -> 64.2 | Improved |
Closest papers by meaning
- Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection (ECCV 2022 · similarity 0.91)
- Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors (ICLR 2021 · similarity 0.90)
- Learning Efficient Object Detection Models with Knowledge Distillation (NeurIPS 2017 · similarity 0.89)
- Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from a Conditional Causal Perspective (AAAI 2023 · similarity 0.89)
- Few-Shot Object Detection via Association and DIscrimination (NeurIPS 2021 · similarity 0.89)
- Distilling Object Detectors With Fine-Grained Feature Imitation (CVPR 2019 · similarity 0.89)
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.
