Name:
Xiao2018TransferLearning.pdf
Size:
23.02Mb
Format:
PDF
Description:
Accepted Manuscript
Type
ArticleKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionComputer Science Program
Visual Computing Center (VCC)
Date
2018-04-30Preprint Posting Date
2017-03-27Online Publication Date
2018-04-30Print Publication Date
2018-08Permanent link to this record
http://hdl.handle.net/10754/626486
Metadata
Show full item recordAbstract
Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass discriminative training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.Citation
Xiao L, Heide F, Heidrich W, Schölkopf B, Hirsch M (2018) Discriminative Transfer Learning for General Image Restoration. IEEE Transactions on Image Processing 27: 4091–4104. Available: http://dx.doi.org/10.1109/TIP.2018.2831925.Sponsors
This work was in part supported by King Abdullah University of Science and Technology under individual baseline funding. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Weisi Lin.arXiv
1703.09245Additional Links
https://ieeexplore.ieee.org/document/8352765/ae974a485f413a2113503eed53cd6c53
10.1109/TIP.2018.2831925