no code implementations • ECCV 2020 • Xinpeng Xie, Jia-Wei Chen, Yuexiang Li, Linlin Shen, Kai Ma, Yefeng Zheng
Recent generative adversarial network (GAN) based methods (e. g., CycleGAN) are prone to fail at preserving image-objects in image-to-image translation, which reduces their practicality on tasks such as domain adaptation.
no code implementations • 22 Jul 2020 • Xinpeng Xie, Jia-Wei Chen, Yuexiang Li, Linlin Shen, Kai Ma, Yefeng Zheng
Due to the wide existence and large morphological variances of nuclei, accurate nuclei instance segmentation is still one of the most challenging tasks in computational pathology.
no code implementations • 22 Jul 2020 • Xinpeng Xie, Jia-Wei Chen, Yuexiang Li, Linlin Shen, Kai Ma, Yefeng Zheng
Domain shift between medical images from multicentres is still an open question for the community, which degrades the generalization performance of deep learning models.
no code implementations • 20 Jul 2020 • Yuexiang Li, Jia-Wei Chen, Xinpeng Xie, Kai Ma, Yefeng Zheng
A novel pseudo-label (namely self-loop uncertainty), generated by recurrently optimizing the neural network with a self-supervised task, is adopted as the ground-truth for the unlabeled images to augment the training set and boost the segmentation accuracy.
no code implementations • 24 Dec 2018 • WenTing Chen, Xinpeng Xie, Xi Jia, Linlin Shen
We also evaluate our approach qualitatively and quantitatively on facial attribute and facial expression synthesis.
no code implementations • 6 Jul 2018 • Yuexiang Li, Xinpeng Xie, Linlin Shen, Shaoxiong Liu
However, the usage of deep learning networks for the pathological image analysis encounters several challenges, e. g. high resolution (gigapixel) of pathological images and lack of annotations of cancer areas.
no code implementations • 18 Apr 2018 • Xinpeng Xie, Yuexiang Li, Linlin Shen
Our RAL is applied to the training set of a simple convolutional neural network (CNN) to remove mislabeled images.