dc.contributor.author | Yu, X | |
dc.contributor.author | Zhang, H | |
dc.contributor.author | Luo, C | |
dc.contributor.author | Qi, H | |
dc.contributor.author | Ren, P | |
dc.date.accessioned | 2018-02-23T14:21:05Z | |
dc.date.issued | 2018-02-23 | |
dc.description.abstract | We develop an automatic oil spill segmentation
method in terms of f-divergence minimization. We exploit fdivergence
for measuring the disagreement between the distributions
of ground-truth and generated oil spill segmentations.
To render tractable optimization, we minimize the tight lower
bound of the f-divergence by adversarial training a regressor
and a generator, which are structured in different forms of deep
neural networks separately. The generator aims at producing
accurate oil spill segmentation, while the regressor characterizes
discriminative distributions with respect to true and generated
oil spill segmentations. It is the co-play between the generator net
and the regressor net against each other that achieves a minimal
of the maximum lower bound for the f-divergence. The adversarial
strategy enhances the representational powers of both the
generator and the regressor and avoids requesting large amounts
of labelled data for training the deep network parameters. In
addition, the trained generator net enables automatic oil spill
detection that does not require manual initialization. Benefiting
from the comprehensiveness of f-divergence for characterizing
diversified distributions, our framework can accurately segment
variously shaped oil spills in noisy SAR images. Experimental
results validate the effectiveness of the proposed oil spill segmentation
framework. | en_GB |
dc.description.sponsorship | This work was supported in part by National Natural Science Foundation
of China (Project No. 61671481), Qingdao Applied Fundamental Research
(Project No. 16-5-1-11-jch), and The Fundamental Research Funds for the
Central Universities under Project 18CX05014A. | en_GB |
dc.identifier.citation | Published online 23 February 2018 | en_GB |
dc.identifier.doi | 10.1109/TGRS.2018.2803038 | |
dc.identifier.uri | http://hdl.handle.net/10871/31634 | |
dc.language.iso | en | en_GB |
dc.publisher | Institute of Electrical and Electronics Engineers | en_GB |
dc.rights | © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.” | en_GB |
dc.subject | Oil spill segmentation | en_GB |
dc.subject | f-divergence minimization | en_GB |
dc.subject | adversarial learning | en_GB |
dc.subject | synthetic aperture radar (SAR) image processing. | en_GB |
dc.title | Oil spill segmentation via adversarial f -divergence learning | en_GB |
dc.type | Article | en_GB |
dc.identifier.issn | 0196-2892 | |
dc.description | This is the author accepted manuscript. The final version is available from IEEE via the DOI in this record | en_GB |
dc.identifier.journal | IEEE Transactions on Geoscience and Remote Sensing | en_GB |