Relation Networks for Object Detection

Han Hu, Jiayuan Gu, Zheng Zhang, Jifeng Dai, Yichen Wei; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 3588-3597


Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learning era. All state-of-the-art object detection systems still rely on recognizing object instances extbf{individually}, without exploiting their relations during learning. This work proposes an object relation module. It processes a set of objects extbf{simultaneously} through interaction between their appearance feature and geometry, thus allowing modeling of their relations. It is lightweight and in-place. It does not require additional supervision and is easy to embed in existing networks. It is shown effective on improving object recognition and duplicate removal steps in the modern object detection pipeline. It verifies the efficacy of modeling object relations in CNN based detection. It gives rise to the extbf{first fully end-to-end object detector}.

Related Material

[pdf] [arXiv] [video]
author = {Hu, Han and Gu, Jiayuan and Zhang, Zheng and Dai, Jifeng and Wei, Yichen},
title = {Relation Networks for Object Detection},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}