Oil spill segmentation via adversarial f -divergence learning
IEEE Transactions on Geoscience and Remote Sensing
Institute of Electrical and Electronics Engineers
© 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.”
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.
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.
This is the author accepted manuscript. The final version is available from IEEE via the DOI in this record
Published online 23 February 2018