PercepPan: Towards unsupervised pan-sharpening based on perceptual loss

Changsheng Zhou, Jiangshe Zhang, Junmin Liu, Chunxia Zhang, Rongrong Fei, Shuang Xu

科研成果: 期刊稿件文章同行评审

41 引用 (Scopus)

摘要

In the literature of pan-sharpening based on neural networks, high resolution multispectral images as ground-truth labels generally are unavailable. To tackle the issue, a common method is to degrade original images into a lower resolution space for supervised training under the Wald's protocol. In this paper, we propose an unsupervised pan-sharpening framework, referred to as "perceptual pan-sharpening". This novel method is based on auto-encoder and perceptual loss, and it does not need the degradation step for training. For performance boosting, we also suggest a novel training paradigm, called "first supervised pre-training and then unsupervised fine-tuning", to train the unsupervised framework. Experiments on the QuickBird dataset show that the framework with different generator architectures could get comparable results with the traditional supervised counterpart, and the novel training paradigm performs better than random initialization. When generalizing to the IKONOS dataset, the unsupervised framework could still get competitive results over the supervised ones.

源语言英语
文章编号2318
期刊Remote Sensing
12
14
DOI
出版状态已出版 - 1 7月 2020
已对外发布

指纹

探究 'PercepPan: Towards unsupervised pan-sharpening based on perceptual loss' 的科研主题。它们共同构成独一无二的指纹。

引用此