论文标题
深层图像翻译，具有基于亲和力的更改，用于无监督的多模式更改检测
Deep Image Translation with an Affinity-Based Change Prior for Unsupervised Multimodal Change Detection
论文作者
论文摘要
带有卷积神经网络的图像翻译最近已被用作多模式变化检测的一种方法。现有方法通过利用变更领域的监督信息来训练网络，但是并非总是可用。无监督问题设置的主要挑战是避免变化像素会影响翻译功能的学习。我们提出了两个新的网络体系结构，该架构训练有损失功能，这些功能由先验加权，以减少变更像素对学习目标的影响。先验的变化是以无监督的方式得出的，该方式是由域特异性亲和力矩阵捕获的关系像素信息。具体而言，我们使用与绝对亲和力差异矩阵相关的顶点度，并证明了它们与周期一致性和对抗性训练相结合的效用。将提出的神经网络与最新算法进行比较。在三个真实数据集上进行的实验显示了我们方法论的有效性。
Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. A main challenge in the unsupervised problem setting is to avoid that change pixels affect the learning of the translation function. We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective. The change prior is derived in an unsupervised fashion from relational pixel information captured by domain-specific affinity matrices. Specifically, we use the vertex degrees associated with an absolute affinity difference matrix and demonstrate their utility in combination with cycle consistency and adversarial training. The proposed neural networks are compared with state-of-the-art algorithms. Experiments conducted on three real datasets show the effectiveness of our methodology.
