DeFCN: End-to-End Object Detection with Fully Convolutional Network

December 2020

tl;dr: End to end object detection with one-to-one label assignment.

Overall impression

The study build upon FCOS. DeFCN points out that the one-to-many label assignment makes NMS necessary. Thus a good one-to-one policy is the key. The paper is also inspired by MultiBox and DETR to use bipartite matching as the matching cost, to allow neural network to learn a better assignment policy.

DeFCN and OneNet:

Key ideas

Technical details