Research map / Detection and segmentation / Weakly supervised detection and segmentation
W2F: A Weakly-Supervised to Fully-Supervised Framework 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 a fully supervised detector trained from top-scoring WSD pseudo boxes (ablation) | WSD · PASCAL VOC 2007 test | mAP: 41.6 -> 45.8 | Helped |
| Add PGE to mine pseudo boxes for object instances (ablation) | WSD+FSD1 · PASCAL VOC 2007 test | mAP: 45.8 -> 51.7 | Helped |
| Add PGA to refine PGE pseudo boxes and use Faster-RCNN (ablation) | WSD+PGE+FSD1 · PASCAL VOC 2007 test | mAP: 51.7% -> 52.4% | Helped |
| Add a fully supervised detector trained from top-scoring WSD pseudo boxes (ablation) | WSD · PASCAL VOC 2012 test | mAP: 39.6 -> 42.4 | Helped |
| Add PGE to mine pseudo boxes for object instances (ablation) | WSD+FSD1 · PASCAL VOC 2012 test | mAP: 42.4 -> 47.3 | Helped |
| Add PGA to refine PGE pseudo boxes and use Faster-RCNN (ablation) | WSD+PGE+FSD1 · PASCAL VOC 2012 test | mAP: 47.3 -> 47.8 | Helped |
| Add a fully supervised detector trained from top-scoring WSD pseudo boxes (ablation) | WSD · PASCAL VOC 2007 trainval | CorLoc: 61.4% to 65.0% | Helped |
| Add PGE to mine pseudo boxes for object instances (ablation) | WSD+FSD1 · PASCAL VOC 2007 trainval | CorLoc: 65.0% to 69.4% | Helped |
| Add PGA to refine PGE pseudo boxes and use Faster-RCNN (ablation) | WSD+PGE+FSD1 · PASCAL VOC 2007 trainval | CorLoc: 69.4% to 70.3% | Helped |
| Use multi-scale training and testing instead of single-scale training and testing (ablation) | WSD+PGE+PGA+FSD2 · PASCAL VOC 2007 test | mAP: 49.0 -> 52.4 | Helped |
| Use multi-scale testing instead of single-scale testing with multi-scale training (ablation) | WSD+PGE+PGA+FSD2 · PASCAL VOC 2007 test | mAP: 50.0 -> 52.4 | Helped |
Closest papers by meaning
- Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection (CVPR 2016 · similarity 0.92)
- Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection (CVPR 2020 · similarity 0.91)
- Partial Weakly-Supervised Oriented Object Detection (CVPR 2026 · similarity 0.90)
- Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity (NeurIPS 2021 · similarity 0.90)
- Object Instance Mining for Weakly Supervised Object Detection (AAAI 2020 · similarity 0.90)
- Relational Matching for Weakly Semi-Supervised Oriented Object Detection (CVPR 2024 · 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.