We introduce Displacement Aware Relation Module (DisARM), a novel neural network module for enhancing the performance of 3D object detection in point cloud scenes. The core idea of our method is that contextual information is critical to tell the difference when the instance geometry is incomplete or featureless. We find that relations between proposals provide a good representation to describe the context. However, adopting relations between all the object or patch proposals for detection is inefficient, and an imbalanced combination of local and global relations brings extra noise that could mislead the training. Rather than working with all relations, we found that training with relations only between the most representative ones, or anchors, can significantly boost the detection performance. A good anchor should be semantic-aware with no ambiguity and independent with other anchors as well. To find the anchors, we first perform a preliminary relation anchor module with an objectness-aware sampling approach and then devise a displacement-based module for weighing the relation importance for better utilization of contextual information. This lightweight relation module leads to significantly higher accuracy of object instance detection when being plugged into the state-of-the-art detectors. Evaluations on the public benchmarks of real-world scenes show that our method achieves state-of-the-art performance on both SUN RGB-D and ScanNet V2.
UCAD: Uncertainty-guided Contour-aware Displacement for semi-supervised medical image segmentation
University of Science and Technology of China（科学技术大学）；Suzhou Institute for Advanced Research（苏州先进研究院）；State Key Laboratory of Precision and Intelligent Chemistry（精密与智能化学国家重点实验室）
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；University of Pittsburgh（匹兹堡大学）；Kuaishou Technology（快手科技）
采样、分组和聚合是点云多尺度分析中的三个重要组成部分。在本文中，我们提出了一种新的数据驱动的采样器学习策略逐点分析任务。与广泛使用的采样技术不同，Faraday Point Sampling（FPS），我们建议联合学习采样和下游应用程序。我们的关键见解是，像FPS这样的均匀采样方法并不总是最适合不同的任务：在边界区域周围采样更多的点可以使逐点分类更容易分割。为此，我们提出了一种新的采样器学习策略，该策略学习由任务相关的地面实况信息监督的采样点位移，并且可以与底层任务联合训练。我们进一步展示了我们的方法在各种逐点分析任务，包括语义部分分割，点云完成，和关键点检测。我们的实验表明，在各种基于点的网络中，采样器和任务的联合学习比使用FPS带来更好的性能。
CAD: Confidence-Aware Adaptive Displacement for Semi-Supervised Medical Image Segmentation
College of Information and Intelligence, Hunan Agricultural University（湖南农业大学信息与智能科学学院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）
Real-time prediction of breast cancer sites using deformation-aware graph neural network
Yonsei University, School of Mathematics and Computing (Computational Science and Engineering)（延世大学数学与计算科学学院）；Yonsei University, Division of Software（延世大学软件系）；Yonsei University College of Medicine, Department of Radiation Oncology（延世大学医学院放射肿瘤科）；Korea Institute of Science and Technology, Bionics Research Center（韩国科学技术院生物医学研究中心）；Graduate School of Artificial Intelligence, Pohang University of Science and Technology (POSTECH)（釜山科学技术大学人工智能研究生院）
Side-Aware Boundary Localization for More Precise Object Detection
The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）；Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）
Frequency-aware Feature Fusion for Dense Image Prediction
Beijing Institute of Technology（北京理工大学）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；RIKEN AIP（理化学研究所人工智能项目）；RCAST, The University of Tokyo（东京大学先进科学技术研究中心）；Research Center for Advanced Science and Technology, The University of Tokyo（东京大学先进科学技术研究中心）；Department of Automation, Tsinghua University（清华大学自动化系）
