Model card
SSD300 (VGG-16).
Google / UNCopen-source~24M paramsSingle-shot multibox detector with VGG-16 backbone, 300x300 input
Single-shot detector using multi-scale feature maps and default boxes. 300x300 input variant. Pascal VOC 2012 test: 72.4 mAP (VOC07+12), 77.5 mAP (+COCO pre-training). ECCV 2016. arxiv:1512.02325.
§ 01 · Benchmarks
Every benchmark SSD300 (VGG-16) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Pascal VOC 2012 | Computer Vision · Object Detection | mAP | 72.4% | #2 | 2015-12-08 | source ↗ |
| 02 | Pascal VOC 2012 | Computer Vision · Object Detection | mAP-coco-pretrain | 77.5% | #2 | 2015-12-08 | 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 SSD300 (VGG-16) actually performs.
§ 03 · Papers
1 paper with results for SSD300 (VGG-16).
- 2015-12-08· Computer Vision· 2 results
SSD: Single Shot MultiBox Detector
§ 04 · Related models
Other Google / UNC models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.