The Chinese University of Hong Kong

About: The Chinese University of Hong Kong is a education organization based out in Hong Kong, China. It is known for research contribution in the topics: Population & Cancer. The organization has 43411 authors who have published 93672 publications receiving 3066651 citations.

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

Abstract: Convolutional neural networks (CNNs) have achieved great successes in many computer vision problems. Unlike existing works that designed CNN architectures to improve performance on a single task of a single domain and not generalizable, we present IBN-Net, a novel convolutional architecture, which remarkably enhances a CNN’s modeling ability on one domain (e.g. Cityscapes) as well as its generalization capacity on another domain (e.g. GTA5) without finetuning. IBN-Net carefully integrates Instance Normalization (IN) and Batch Normalization (BN) as building blocks, and can be wrapped into many advanced deep networks to improve their performances. This work has three key contributions. (1) By delving into IN and BN, we disclose that IN learns features that are invariant to appearance changes, such as colors, styles, and virtuality/reality, while BN is essential for preserving content related information. (2) IBN-Net can be applied to many advanced deep architectures, such as DenseNet, ResNet, ResNeXt, and SENet, and consistently improve their performance without increasing computational cost. (3) When applying the trained networks to new domains, e.g. from GTA5 to Cityscapes, IBN-Net achieves comparable improvements as domain adaptation methods, even without using data from the target domain. With IBN-Net, we won the 1st place on the WAD 2018 Challenge Drivable Area track, with an mIoU of 86.18%.

Image completion with structure propagation

Abstract: In this paper, we introduce a novel approach to image completion, which we call structure propagation. In our system, the user manually specifies important missing structure information by extending a few curves or line segments from the known to the unknown regions. Our approach synthesizes image patches along these user-specified curves in the unknown region using patches selected around the curves in the known region. Structure propagation is formulated as a global optimization problem by enforcing structure and consistency constraints. If only a single curve is specified, structure propagation is solved using Dynamic Programming. When multiple intersecting curves are specified, we adopt the Belief Propagation algorithm to find the optimal patches. After completing structure propagation, we fill in the remaining unknown regions using patch-based texture synthesis. We show that our approach works well on a number of examples that are challenging to state-of-the-art techniques.

Type 2 diabetes in East Asians: similarities and differences with populations in Europe and the United States

Abstract: There is an epidemic of diabetes in Asia. Type 2 diabetes develops in East Asian patients at a lower mean body mass index (BMI) compared with those of European descent. At any given BMI, East Asians have a greater amount of body fat and a tendency to visceral adiposity. In Asian patients, diabetes develops at a younger age and is characterized by early β cell dysfunction in the setting of insulin resistance, with many requiring early insulin treatment. The increasing proportion of young-onset and childhood type 2 diabetes is posing a particular threat, with these patients being at increased risk of developing diabetic complications. East Asian patients with type 2 diabetes have a higher risk of developing renal complications than Europeans and, with regard to cardiovascular complications, a predisposition for developing strokes. In addition to cardiovascular–renal disease, cancer is emerging as the other main cause of mortality. While more research is needed to explain these interethnic differences, urgent and concerted actions are needed to raise awareness, facilitate early diagnosis, and encourage preventive strategies to combat these growing disease burdens.