Convolutional feature pyramid fusion via attention network

Sangryul Jeon, Seungryong Kim, Kwanghoon Sohn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a novel fusion scheme between multiple intermediate convolutional features within convolutional neurual network (CNN) for dense correspondence estimation. In contrast to existing CNN-based descriptors that utilize a single convolutional activation, our approach jointly uses multiple intermediate features of CNN through the attention weight that balances the contribution of each features. We formulate the overall network as two sub-networks, correspondence network and attention network. The correspondence network is designed to provide multiple intermediate matching costs while the attention network is to learn the optimal weight between them. These two networks are learned in a joint manner to boost the correspondence estimation performance. Experiments demonstrate that our proposed method outperforms the state-of-the-art methods on various correspondence estimation tasks including depth estimation, optical flow, and semantic correspondence.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages1007-1011
Number of pages5
Volume2017-September
ISBN (Electronic)9781509021758
DOIs
Publication statusPublished - 2018 Feb 20
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: 2017 Sep 172017 Sep 20

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period17/9/1717/9/20

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Jeon, S., Kim, S., & Sohn, K. (2018). Convolutional feature pyramid fusion via attention network. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (Vol. 2017-September, pp. 1007-1011). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8296433