Research map / Detection and segmentation / CNN features
Single-Shot Refinement Neural Network for Object Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 negative anchor filtering (ablation) | RefineDet320 · PASCAL VOC 2007 test | mAP (%): 79.5% vs. 80.0%; 0.5% | Helped |
| Add two-step cascaded regression using refined anchors (ablation) | RefineDet320 · PASCAL VOC 2007 test | mAP (%): 77.3% to 79.5%; 2.2% | Helped |
| Add transfer connection blocks (ablation) | RefineDet320 · PASCAL VOC 2007 test | mAP (%): 76.2% vs. 77.3%; 1.1% | Helped |
| Increase input size from 320×320 to 512×512 | RefineDet with VGG-16 · MS COCO test-dev | AP: 29.4% to 33.0% | Helped |
| Use multi-scale testing | RefineDet512 with ResNet-101 · MS COCO test-dev | AP: 36.4% to 41.8% | Helped |
| Use ResNet-101 instead of VGG-16 | RefineDet512 · MS COCO test-dev | AP: 33.0 to 36.4 | Helped |
Closest papers by meaning
- Dynamic Refinement Network for Oriented and Densely Packed Object Detection (CVPR 2020 · similarity 0.87)
- Proper Reuse of Image Classification Features Improves Object Detection (CVPR 2022 · similarity 0.87)
- ScratchDet: Training Single-Shot Object Detectors From Scratch (CVPR 2019 · similarity 0.85)
- Selective Refinement Network for High Performance Face Detection (AAAI 2019 · similarity 0.85)
- Few-Shot Object Detection via Classification Refinement and Distractor Retreatment (CVPR 2021 · similarity 0.85)
- DetNAS: Backbone Search for Object Detection (NeurIPS 2019 · similarity 0.85)
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.