-
Notifications
You must be signed in to change notification settings - Fork 6.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Improve the accuracy of Detection & Segmentation models by using SOTA recipes and primitives #5307
Comments
We recently did some experiments on the pre-trained backbone and found that using TIMM's ResNet training method as pretrain
More details can be found in open-mmlab/mmdetection#7001 And I learned that torchvision also updated a new resnet pre-training method recently in #5201 and it is a SOTA ResNet50. Do you have some experiments on faster rcnn using this pretrained model? Wondering how many improvements can achieve. |
@RangiLyu I don't have yet these numbers but we plan to do such experiments soon after we add some new primitives for detection. I'm currently scoping which techniques should be added (see here for some early work). The metrics that appear on this issue were moved from #3995 and was written prior doing any work on ResNet50. BTW I wouldn't be surprised if at the end we end up training the detection models from scratch using longer cycles, as this has been the trend for strong recipes the last few years. |
Hi, I run the expriment of RetinaNet with new ResNet50 on detectron2, with the new weights, we can get 41.9 mAP (+about 3.6 compared 38.3 ) (GN + GIoU + multi-scale training trick) |
🚀 The feature
Similar to #3995 but focus on Object Detection and Segmentation.
Kick-off a Batteries Included phase 2 project that will focus on improving object detection and segmentation. After adding the necessary primitives, create a new recipe that improves the accuracy of existing models and retrain them to offer better weights to the community.
Results
Best currently available models achieved:
retinanet_resnet50_fpn
: 36.4 mAPretinanet_resnet50_fpn_v2
: 41.5 mAP (+5.1)maskrcnn_resnet50_fpn
: 37.9 box mAP / 34.6 mask mAPmaskrcnn_resnet50_fpn_v2
: 47.4 box mAP / 41.8 mask mAP (+9.5/+7.2)fasterrcnn_resnet50_fpn
: 37.0 mAPfasterrcnn_resnet50_fpn_v2
: 46.7 mAP (+9.7)The above results were achieved by building on top of work done by @rbgirshick, @pdollar, @vaibhava0, @fmassa and @xiaohu2015.
The text was updated successfully, but these errors were encountered: