21/09/2019 • 1 paper accepted at 2019 ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models

Class Feature Pyramid

We introduce Class Feature Pyramids, a method that traverses the entire network structure and incrementally discovers kernels at different network depths that are informative for a specific class. Our method does not depend on the network’s architecture or the type of 3D convolutions, supporting grouped and depth-wise convolutions, convolutions in fibers, and convolutions in branches.

[arXiv preprint] [Workshop website]