Proceedings

Learning deep structured network for weakly supervised change detection

Salman Khan, Xuming He, Fatih Porikli, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri

Download BibTeX Cite

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. Main track. Pages 2008-2015.

https://doi.org/10.24963/ijcai.2017/279

Keywords

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

Abstract

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.

Salman Khan, Xuming He, Fatih Porikli, Mohammed Bennamoun, Ferdous Sohel, and Roberto Togneri. 2017. Learning deep structured network for weakly supervised change detection. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17. IJCAI, 2008–2015. https://doi.org/10.24963/ijcai.2017/279
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards