What are pretrained weights and initialization weights in Mask R-CNN?

Question

I'm trying to train Mask R-CNN for instance segmentation. Where are some available pretrained models. Are these weights for the whole neural net or only for encoder/backbone (for instance resnet50)? Also there's initializations weights using imagenet or coco. With the latter all weights in decoder are random?

Answer 1

Here are some of the best Mask RCNN implementation,

 1. https://github.com/matterport/Mask_RCNN
 2. https://github.com/CharlesShang/FastMaskRCNN
 3. https://github.com/multimodallearning/pytorch-mask-rcnn
 4. https://github.com/wannabeOG/Mask-RCNN

Pretrained weights and initialization weights are normally for the whole network and not for the backbone.

Recommend you to do your research before posting on stackoverflow. Please go to github and search for Mask RCNN, you'll find loads of repos.