Architecure of Mask R-CNN

In this diagram, we see the two convs. It is said that these convs are a part of the Fully Convolution Network (FCN). In their paper Mask R-CNN (He et al., 2018), they mentioned something about the backbone (ResNets/Feature Pyramid Network ) and the head architecture of the model. I am just wondering how are they related to FCN and the two convs in the diagram. This diagram is also the first figure in their paper, just in case you can't see it.

  • $\begingroup$ Please link the paper to your post for ease. $\endgroup$
    – rgk
    Mar 15, 2019 at 21:40
  • $\begingroup$ Here's the paper: arxiv.org/pdf/1703.06870.pdf $\endgroup$
    – jss367
    Aug 8, 2019 at 16:43

1 Answer 1


The backbone refers to the network which takes as input the image and extracts the feature map upon which the rest of the network is based (the output of the backbone is the first block in your figure). "head" refers to everything after the RoI pooling -- in other words what you've labeled as FCN.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.