Research map / Detection and segmentation / CNN features
Dense Relation Distillation With Context-Aware Aggregation for Few-Shot Object Detection
Hanzhe Hu, Shuai Bai, Aoxue Li, Jinshi Cui, Liwei Wang
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 dense query-support feature matching in place of Meta R-CNN's class-specific prediction (ablation) | Faster R-CNN few-shot detection · PASCAL VOC 2007 test, Novel Set 1, 1-shot | AP50: 21.8 -> 31.1 | Improved |
| add context-aware feature aggregation (ablation) | Meta R-CNN† · PASCAL VOC 2007 test, Novel Set 1, 1-shot | AP50: 21.8 -> 22.0 | Improved |
| add attention-based aggregation to CFA (ablation) | Meta R-CNN† with CFA · PASCAL VOC 2007 test, Novel Set 1, 1-shot | AP50: 22.0 -> 24.2 | Improved |
| use CFA with the dense-relation model (ablation) | DCNet · PASCAL VOC 2007 test, Novel Set 1, 1-shot | AP50: 31.1 -> 32.9 | Improved |
| use all three RoI pooling resolutions (4, 8, and 12) (ablation) | DCNet · PASCAL VOC 2007 test, Novel Set 1, 10-shot | AP50: 58.7 -> 59.6 | Improved |
| use RoI pooling resolution 12 rather than resolution 8 alone (ablation) | DCNet · PASCAL VOC 2007 test, Novel Set 1, 10-shot | AP50: 57.2 -> 58.7 | Improved |
| add dense relation distillation (ablation) | few-shot object detection · PASCAL VOC 2007 test, Novel Set 1, 1-shot | AP50: 21.8 -> 31.1 | Improved |
| combine DRD and CFA in DCNet | few-shot object detection · PASCAL VOC 2007 test, Novel Set 3, 5-shot | AP50: 43.8 -> 42.6 | Hurt |
Closest papers by meaning
- Relation Distillation Networks for Video Object Detection (ICCV 2019 · similarity 0.88)
- Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection (ECCV 2022 · similarity 0.88)
- Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector (CVPR 2020 · similarity 0.88)
- Prediction-Guided Distillation for Dense Object Detection (ECCV 2022 · similarity 0.88)
- Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024 · similarity 0.87)
- Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations (ECCV 2022 · similarity 0.87)
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.
