arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.06264cs.CVcs.LG
收藏

高分辨率语义一致的图像到图像翻译

High-resolution semantically-consistent image-to-image translation

University of Winnipeg(温尼伯大学);Natural Resources Canada(加拿大自然资源部);Canada Centre for Mapping and Earth Observation(加拿大测绘与地球观测中心)

Mikhail Sokolov, Christopher Henry, Joni Storie, Christopher Storie, Victor Alhassan, Mathieu Turgeon-Pelchat

摘要:

近年来,深度学习已经成为遥感科学家最有效的计算机视觉工具之一。然而,缺乏训练标签的遥感数据集意味着科学家需要解决的领域自适应问题,以缩小卫星图像数据集之间的差异。因此,经过训练的图像分割模型可以更好地推广和使用现有的标签集,而不需要新的标签。本文提出了一种无监督的领域自适应模型,该模型在风格转换阶段保持图像的语义一致性和像素质量。本文的主要贡献是提出了改进的架构的SemI 2 I模型,这显着提高了所提出的模型的性能,使其具有竞争力的国家的最先进的CyCADA模型。第二个贡献是在WorldView-2和SPOT-6等遥感多波段数据集上测试CyCADA模型。该模型在风格转换阶段保持了图像的语义一致性和像素质量。因此,与SemI 2 I模型相比,在适应图像上训练的语义分割模型显示出显著的性能增益,并达到与最先进的CyCADA模型相似的结果。未来的发展所提出的方法可能包括生态域转移,{ \em先验}的数据分布方面的数据集质量的评估,或探索的内部架构的领域自适应模型。

英文摘要:

Deep learning has become one of remote sensing scientists' most efficient computer vision tools in recent years. However, the lack of training labels for the remote sensing datasets means that scientists need to solve the domain adaptation problem to narrow the discrepancy between satellite image datasets. As a result, image segmentation models that are then trained, could better generalize and use an existing set of labels instead of requiring new ones. This work proposes an unsupervised domain adaptation model that preserves semantic consistency and per-pixel quality for the images during the style-transferring phase. This paper's major contribution is proposing the improved architecture of the SemI2I model, which significantly boosts the proposed model's performance and makes it competitive with the state-of-the-art CyCADA model. A second contribution is testing the CyCADA model on the remote sensing multi-band datasets such as WorldView-2 and SPOT-6. The proposed model preserves semantic consistency and per-pixel quality for the images during the style-transferring phase. Thus, the semantic segmentation model, trained on the adapted images, shows substantial performance gain compared to the SemI2I model and reaches similar results as the state-of-the-art CyCADA model. The future development of the proposed method could include ecological domain transfer, {\em a priori} evaluation of dataset quality in terms of data distribution, or exploration of the inner architecture of the domain adaptation model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑