On ImageNet Detection, a ResNet-101 Faster R-CNN single model reports 60.5% mAP on val2 and 58.8% on test, while a three-model ensemble reaches 63.6% and 62.1%. The ensemble won ILSVRC 2015 detection and is reported to lead second place by 8.5 absolute points.

On ImageNet Detection, a ResNet-101 Faster R-CNN single model reports 60.5% mAP on val2 and 58.8% on test, while a three-model ensemble reaches 63.6% and 62.1%. The ensemble won ILSVRC 2015 detection and is reported to lead second place by 8.5 absolute points. · CiteArk

Measurement results

0/6 assessed

0 supported0 disputed or conflicting6 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
43.9%	—	Not assessed
60.5%	—	Not assessed
58.8%	—	Not assessed
63.6%	—	Not assessed
62.1%	—	Not assessed
8.5 mAP points	—	Not assessed

On ImageNet Detection, a ResNet-101 Faster R-CNN single model reports 60.5% mAP on val2 and 58.8% on test, while a three-model ensemble reaches 63.6% and 62.1%. The ensemble won ILSVRC 2015 detection and is reported to lead second place by 8.5 absolute points.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results