In the following code inside the HKRM implicit module, the Identity matrix is added num_A times to the adjacency matrix that defines a particular relation graph. Therefore, the main diagonal is numA * I, while all the other elements are lesser than 1. Even after normalization, this indicates that the main contribution to a region i would be itself, and negligible contributions from other regions j.
In the following code inside the HKRM implicit module, the Identity matrix is added
num_A
times to the adjacency matrix that defines a particular relation graph. Therefore, the main diagonal isnumA * I
, while all the other elements are lesser than 1. Even after normalization, this indicates that the main contribution to a regioni
would be itself, and negligible contributions from other regionsj
.https://github.com/chanyn/HKRM/blob/master/lib/model/HKRM/faster_rcnn_HKRM.py#L58
If you could please elaborate the reasoning behind this design, it would be a big help. Thank you.