no code implementations • 8 Sep 2018 • Gao Xu, Yongming Zhang, Qixing Zhang, Gaohua Lin, Zhong Wang, Yang Jia, Jinjun Wang
The deep feature map is combined with the saliency map to predict the existence of smoke in an image.
no code implementations • 24 Sep 2017 • Gao Xu, Yongming Zhang, Qixing Zhang, Gaohua Lin, Jinjun Wang
The existed researches mainly work on the adaptation to samples extracted from original annotated samples.
no code implementations • 31 Mar 2017 • Gao Xu, Yongming Zhang, Qixing Zhang, Gaohua Lin, Jinjun Wang
Considering that the appearance gap (dataset bias) between synthetic and real smoke images degrades significantly the performance of the trained model on the test set composed fully of real images, we build deep architectures based on domain adaptation to confuse the distributions of features extracted from synthetic and real smoke images.