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.

Ground State of N Coupled Nonlinear Schrodinger Equations in {\mathbb{R}}^n, n \leq 3

Abstract: We establish some general theorems for the existence and nonexistence of ground state solutions of steady-state N coupled nonlinear Schrodinger equations. The sign of coupling constants β ij ’s is crucial for the existence of ground state solutions. When all β ij ’s are positive and the matrix Σ is positively definite, there exists a ground state solution which is radially symmetric. However, if all β ij ’s are negative, or one of β ij ’s is negative and the matrix Σ is positively definite, there is no ground state solution. Furthermore, we find a bound state solution which is non-radially symmetric when N=3.

Learning Lightweight Lane Detection CNNs by Self Attention Distillation

Abstract: Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations. Without learning from much richer context, these models often fail in challenging scenarios, e.g., severe occlusion, ambiguous lanes, and poor lighting conditions. In this paper, we present a novel knowledge distillation approach, i.e., Self Attention Distillation (SAD), which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels. Specifically, we observe that attention maps extracted from a model trained to a reasonable level would encode rich contextual information. The valuable contextual information can be used as a form of ‘free’ supervision for further representation learning through performing top- down and layer-wise attention distillation within the net- work itself. SAD can be easily incorporated in any feed- forward convolutional neural networks (CNN) and does not increase the inference time. We validate SAD on three popular lane detection benchmarks (TuSimple, CULane and BDD100K) using lightweight models such as ENet, ResNet- 18 and ResNet-34. The lightest model, ENet-SAD, performs comparatively or even surpasses existing algorithms. Notably, ENet-SAD has 20 × fewer parameters and runs 10 × faster compared to the state-of-the-art SCNN, while still achieving compelling performance in all benchmarks.

3D Graph Neural Networks for RGBD Semantic Segmentation

Abstract: RGBD semantic segmentation requires joint reasoning about 2D appearance and 3D geometric information. In this paper we propose a 3D graph neural network (3DGNN) that builds a k-nearest neighbor graph on top of 3D point cloud. Each node in the graph corresponds to a set of points and is associated with a hidden representation vector initialized with an appearance feature extracted by a unary CNN from 2D images. Relying on recurrent functions, every node dynamically updates its hidden representation based on the current status and incoming messages from its neighbors. This propagation model is unrolled for a certain number of time steps and the final per-node representation is used for predicting the semantic class of each pixel. We use back-propagation through time to train the model. Extensive experiments on NYUD2 and SUN-RGBD datasets demonstrate the effectiveness of our approach.

Endoscopic retreatment compared with surgery in patients with recurrent bleeding after initial endoscopic control of bleeding ulcers.

Abstract: Background and Methods After endoscopic treatment to control bleeding of peptic ulcers, bleeding recurs in 15 to 20 percent of patients. In a prospective, randomized study, we compared endoscopic retreatment with surgery after initial endoscopy. Over a 40-month period, 1169 of 3473 adults who were admitted to our hospital with bleeding peptic ulcers underwent endoscopy to reestablish hemostasis. Of 100 patients with recurrent bleeding, 7 patients with cancer and 1 patient with cardiac arrest were excluded from the study; 48 patients were randomly assigned to undergo immediate endoscopic retreatment and 44 were assigned to undergo surgery. The type of operation used was left to the surgeon. Bleeding was considered to have recurred in the event of any one of the following: vomiting of fresh blood, hypotension and melena, or a requirement for more than four units of blood in the 72-hour period after endoscopic treatment. Results Of the 48 patients who were assigned to endoscopic retreatment, 35 had long-term...