Type
Conference PaperKAUST Department
Applied Mathematics & Computational SciApplied Mathematics and Computational Science Program
Computational Vision Lab
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
Visual Computing Center (VCC)
Date
2020-08-05Preprint Posting Date
2020-04-10Online Publication Date
2020-08-05Print Publication Date
2020-06Permanent link to this record
http://hdl.handle.net/10754/662571
Metadata
Show full item recordAbstract
We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a different domain, a problem known as unsupervised domain adaptation. We focus on the task of semantic segmentation, where annotated synthetic data are aplenty, but annotating real data is laborious. The first criterion, inspired by visual psychophysics, is that the map between the two image domains be phase-preserving. This restricts the set of possible learned maps, while enabling enough flexibility to transfer semantic information. The second criterion aims to leverage ecological statistics, or regularities in the scene which are manifest in any image of it, regardless of the characteristics of the illuminant or the imaging sensor. It is implemented using a deep neural network that scores the likelihood of each possible segmentation given a single un-annotated image. Incorporating these two priors in a standard domain adaptation framework improves performance across the board in the most common unsupervised domain adaptation benchmarks for semantic segmentation.Citation
Yang, Y., Lao, D., Sundaramoorthi, G., & Soatto, S. (2020). Phase Consistent Ecological Domain Adaptation. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.00903Sponsors
Research supported by ARO W911NF-17-1-0304 and ONR N00014-19-1-2066. Dong Lao is supported by KAUST through the VCC Center Competitive FundingConference/Event name
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)ISBN
978-1-7281-7169-2arXiv
2004.04923Additional Links
https://ieeexplore.ieee.org/document/9157388/https://ieeexplore.ieee.org/document/9157388/
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9157388
ae974a485f413a2113503eed53cd6c53
10.1109/CVPR42600.2020.00903