Learning deep structured network for weakly supervised change detection

Conventional change detection methods require a large number of images to learn background models or depend on tedious pixel-level labeling by humans. In this paper, we present a weakly supervised approach that needs only image-level labels to simultaneously detect and localize changes in a pair of images. To this end, we employ a deep neural network with DAG topology to learn patterns of change from image-level labeled training data. On top of the initial CNN activations, we define a CRF model to incorporate the local differences and context with the dense connections between individual pixels. We apply a constrained mean-field algorithm to estimate the pixel-level labels, and use the estimated labels to update the parameters of the CNN in an iterative EM framework. This enables imposing global constraints on the observed foreground probability mass function. Our evaluations on four benchmark datasets demonstrate superior detection and localization performance.

Authors

• Salman Khan Mohamed bin Zayed University of Artificial Intelligence, (MBZUAI), UAE Australian National University, Canberra ACT, Australia
• Xuming He ShanghaiTech University Shanghai Engineering Research Center of Intelligent Vision and Imaging
• Fatih Porikli
• Mohammed Bennamoun
• Ferdous Sohel
• Roberto Togneri

Keywords

• Machine Learning: Machine Learning
• Machine Learning: Semi-Supervised Learning
• Robotics and Vision: Vision and Perception