Background-Mixed Augmentation for Weakly Supervised Change Detection

Change detection (CD) is to decouple object changes ( i.e ., ob- ject missing or appearing) from background changes ( i.e ., environment variations) like light and season variations in two images captured in the same scene over a long time span, presenting critical applications in disaster management, ur- ban development, etc . In particular, the endless patterns of background changes require detectors to have a high gener- alization against unseen environment variations, making this task significantly challenging. Recent deep learning-based methods develop novel network architectures or optimization strategies with paired-training examples, which do not handle the generalization issue explicitly and require the huge man-ual pixel-level annotation efforts. In this work, for the first at- tempt in the CD community, we study the generalization issue of CD from the perspective of data augmentation and develop a novel weakly supervised training algorithm that only needs image-level labels. Different from general augmentation tech- niques for classification, we propose the background-mixed augmentation that is specifically designed for change detec- tion by augmenting examples under the guidance of a set of background changing images and letting deep CD models see diverse environment variations. Moreover, we propose the augmented & real data consistency loss that encourages the generalization increase significantly. Our method as a gen- eral framework can enhance a wide range of existing deep learning-based detectors. We conduct extensive experiments in two public datasets and enhance four state-of-the-art methods, demonstrating the advantages of our method.