no code implementations • CVPR 2020 • Bolei Xu, Jingxin Liu, Xianxu Hou, Bozhi Liu, Guoping Qiu
Previous deep learning approaches to color constancy usually directly estimate illuminant value from input image.
no code implementations • 10 May 2020 • Xianxu Hou, Jingxin Liu, Bolei Xu, Xiaolong Wang, Bozhi Liu, Guoping Qiu
To improve the adversarial robustness of neural networks, adversarial training has been proposed to train networks by injecting adversarial examples into the training data.
no code implementations • 25 Sep 2019 • Xianxu Hou, Jingxin Liu, Bolei Xu, Bozhi Liu, Xin Chen, Mohammad Ilyas, Ian Ellis, Jon Garibaldi, Guoping Qiu
The extensive experiments and ablation study demonstrate the effectiveness of our approach on the domain adaptive segmentation task.
no code implementations • 4 Jun 2019 • Xianxu Hou, Hongming Luo, Jingxin Liu, Bolei Xu, Ke Sun, Yuanhao Gong, Bozhi Liu, Guoping Qiu
In this paper, we propose an effective image denoising method by learning two image priors from the perspective of domain alignment.
no code implementations • 28 Feb 2019 • Bolei Xu, Jingxin Liu, Xianxu Hou, Bozhi Liu, Jon Garibaldi, Ian O. Ellis, Andy Green, Linlin Shen, Guoping Qiu
In this paper, we present a novel deep hybrid attention approach to breast cancer classification.
no code implementations • 19 Jan 2018 • Jingxin Liu, Bolei Xu, Chi Zheng, Yuanhao Gong, Jon Garibaldi, Daniele Soria, Andew Green, Ian O. Ellis, Wenbin Zou, Guoping Qiu
To the best of our knowledge, this is the first end-to-end system that takes a TMA image as input and directly outputs a clinical score.