On PASCAL VOC 2012 test, baseline ResNet-101 improves overall mAP and every printed class AP over baseline VGG-16. The ResNet-101 baseline+++ system trained with COCO plus VOC data and using box refinement, context, and multi-scale testing reaches 83.8% mAP, reported as 10 points above the previous state of the art; all 20 category APs are printed.

On PASCAL VOC 2012 test, baseline ResNet-101 improves overall mAP and every printed class AP over baseline VGG-16. The ResNet-101 baseline+++ system trained with COCO plus VOC data and using box refinement, context, and multi-scale testing reaches 83.8% mAP, reported as 10 points above the previous state of the art; all 20 category APs are printed. · CiteArk

测量结果

已评估 0/64 项

获得支持 0有争议或冲突 0尚未评估 64

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
论文报告	最近可用实测	证据判断
70.4%	—	尚未评估
84.9%	—	尚未评估
79.8%	—	尚未评估
74.3%	—	尚未评估
53.9%	—	尚未评估
49.8%	—	尚未评估
77.5%	—	尚未评估
75.9%	—	尚未评估
88.5%	—	尚未评估
45.6%	—	尚未评估
77.1%	—	尚未评估
55.3%	—	尚未评估

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果