Model card
Faster R-CNN (VGG-16).
Microsoft Researchopen-source~137M paramsTwo-stage detector: RPN + Fast R-CNN with VGG-16 backbone
Seminal two-stage object detector introducing Region Proposal Networks. VGG-16 backbone. Pascal VOC 2012 test: 70.4 mAP (VOC07+12 training), 75.9 mAP (+COCO pre-training). NeurIPS 2015. arxiv:1506.01497.
§ 01 · Benchmarks
Every benchmark Faster R-CNN (VGG-16) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Pascal VOC 2012 | Computer Vision · Object Detection | mAP | 70.4% | #3 | 2015-06-04 | source ↗ |
| 02 | Pascal VOC 2012 | Computer Vision · Object Detection | mAP-coco-pretrain | 75.9% | #3 | 2015-06-04 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where Faster R-CNN (VGG-16) actually performs.
§ 03 · Papers
1 paper with results for Faster R-CNN (VGG-16).
- 2015-06-04· Computer Vision· 2 results
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
§ 04 · Related models
Other Microsoft Research models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.