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

Measurement results

0/64 assessed

0 supported0 disputed or conflicting64 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Reported	Latest observation	Evidence judgment
70.4%	—	Not assessed
84.9%	—	Not assessed
79.8%	—	Not assessed
74.3%	—	Not assessed
53.9%	—	Not assessed
49.8%	—	Not assessed
77.5%	—	Not assessed
75.9%	—	Not assessed
88.5%	—	Not assessed
45.6%	—	Not assessed
77.1%	—	Not assessed
55.3%	—	Not assessed

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results