提出新方法实现遥感影像语义稳健的无监督图像转换
Semantically Robust Unsupervised Image Translation for Paired Remote Sensing Images
- 共享高层网络参数，强制双时相影像映射到同一潜在空间
- 引入跨周期一致性对抗网络，实现双向可逆转换与恢复
- 适合需要精确语义保持的遥感变化检测与分类任务
针对双时相遥感影像变化检测或分类中的图像转换问题，尽管图像成对出现，但仍属无监督学习。且转换过程需严格保持语义一致性，而非生成多模态输出。为此，本文提出一种新方法——SRUIT（Semantically Robust Unsupervised Image-to-image Translation），确保语义鲁棒性并生成确定性输出。受已有工作启发，该方法挖掘双时相遥感影像的内在特性，设计相应网络结构：首先假设双时相影像因来自同一地理区域而共享同一潜在空间，故让生成器共享高层参数，迫使两个域映射进入同一潜在空间；其次，考虑到地表覆盖类型可在时间周期间相互演变，采用跨周期一致性对抗网络实现双向转换与重构。实验表明，权重共享与跨周期一致性约束使转换图像在显著差异下仍具备良好感知质量与语义保真度。
原文摘要 · Abstract (English)
Image translation for change detection or classification in bi-temporal remote sensing images is unique. Although it can acquire paired images, it is still unsupervised. Moreover, strict semantic preservation in translation is always needed instead of multimodal outputs. In response to these problems, this paper proposes a new method, SRUIT (Semantically Robust Unsupervised Image-to-image Translation), which ensures semantically robust translation and produces deterministic output. Inspired by previous works, the method explores the underlying characteristics of bi-temporal Remote Sensing images and designs the corresponding networks. Firstly, we assume that bi-temporal Remote Sensing images share the same latent space, for they are always acquired from the same land location. So SRUIT makes the generators share their high-level layers, and this constraint will compel two domain mapping to fall into the same latent space. Secondly, considering land covers of bi-temporal images could evolve into each other, SRUIT exploits the cross-cycle-consistent adversarial networks to translate from one to the other and recover them. Experimental results show that constraints of sharing weights and cross-cycle consistency enable translated images with both good perceptual image quality and semantic preservation for significant differences.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。