Skip to content
Deformable Convolutional Networks + MST + Soft-NMS
Branch: master
Clone or download
#6 Compare This branch is 8 commits ahead, 51 commits behind msracver:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
faster_rcnn fix bug Jun 1, 2017
init.bat release May 5, 2017

Deformable ConvNets is initially described in an arxiv tech report.

R-FCN is initially described in a NIPS 2016 paper.

Soft-NMS is initially described in an arxiv tech report.

Our goal was to test Soft-NMS with a state-of-the-art detector, so Deformable-R-FCN was trained on 800x1200 size images with 15 anchors. Multi-Scale testing was also added with 6 scales. Union of all boxes at each scale was computed before performing NMS. Please note that the repository does not include the scripts for multi-scale testing as I just cache the boxes for each different scale and do NMS separately. The scales used in multi-scale testing were as follows, [(480, 800), (576,900), (688, 1100), (800,1200), (1200, 1600), (1400, 2000)].

The trained model can be downloaded from here.

training data testing data mAP mAP@0.5 mAP@0.75 mAP@S mAP@M mAP@L Recall
Baseline D-R-FCN coco trainval coco test-dev 35.7 56.8 38.3 15.2 38.8 51.5
D-R-FCN, ResNet-v1-101, NMS coco trainval coco test-dev 37.4 59.6 40.2 17.8 40.6 51.4 48.3
D-R-FCN, ResNet-v1-101, SNMS coco trainval coco test-dev 38.4 60.1 41.6 18.5 41.6 52.5 53.8
D-R-FCN, ResNet-v1-101, MST, NMS coco trainval coco test-dev 39.8 62.4 43.3 22.6 42.3 52.2 52.9
D-R-FCN, ResNet-v1-101, MST, SNMS coco trainval coco test-dev 40.9 62.8 45.0 23.3 43.6 53.3 60.4
You can’t perform that action at this time.