Capturing global contextual representations by exploiting long-range pixel-pixel dependencies has shown to improve semantic segmentation performance. However, how to do this efficiently is an open question as current approaches of utilising attention schemes or very deep models to increase the models field of view, result in complex models with large memory consumption. Inspired by recent work on graph neural networks, we propose the Self-Constructing Graph (SCG) module that learns a long-range dependency graph directly from the image and uses it to propagate contextual information efficiently to improve semantic segmentation. The module is optimised via a novel adaptive diagonal enhancement method and a variational lower bound that consists of a customized graph reconstruction term and a Kullback-Leibler divergence regularization term. When incorporated into a neural network (SCG-Net), semantic segmentation is performed in an end-to-end manner and competitive performance (mean F1-scores of 92.0% and 89.8% respectively) on the publicly available ISPRS Potsdam and Vaihingen datasets is achieved, with much fewer parameters, and at a lower computational cost compared to related pure convolutional neural network (CNN) based models.
An end-to-end CNN framework for polarimetric vision tasks based on polarization-parameter-constructing network
Army Academy of Artillery and Air Defense, PLA（中国人民解放军陆军炮兵防空兵学院）；Anhui Provincial Key Laboratory of Polarization Imaging Detection Technology（安徽省偏振成像探测技术重点实验室）；School of Internet, Anhui University（安徽大学互联网学院）；Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences（中国科学院安徽光学精密机械研究所）
Two-level Graph Network for Few-Shot Class-Incremental Learning
Suzhou University of Science and Technology（苏州科技大学）；Suzhou Institute of Trade & Commerce（苏州经贸职业技术学院）；Tianjin University（天津大学）；Jiangsu Industrial Intelligent and Low-carbon Technology Engineering Center（江苏省工业智能与低碳技术工程中心）；Suzhou Key Laboratory of Intelligent Low-carbon Technology Application（苏州市智能低碳技术应用重点实验室）
Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
Tencent（腾讯）；Jilin University（吉林大学）；NLPR Institute of Automation CAS（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence UCAS（中国科学院大学人工智能学院）；CASIA-LLVision Joint Lab（中国科学院自动化研究所-联影智能联合实验室）
Learning from Pattern Completion: Self-supervised Controllable Generation
Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Institute of Automation, Chinese Academy of Science（中国科学院自动化研究所）；Peking University（北京大学）；Xi’an Jiaotong University（西安交通大学）；University of Chinese Academy of Science（中国科学院大学）
Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentation
The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）；The Hong Kong University of Science and Technology Shenzhen Research Institute（香港科技大学深圳研究院）
将医学图像分割算法推广到未知领域是计算机辅助诊断和手术的重要研究课题。大多数现有的方法需要在每个源域中的完全标记的数据集。尽管一些研究人员开发了半监督的领域广义方法，但它仍然需要领域标签。提出了一种新的置信度感知的交叉伪监督算法，用于半监督域广义医学图像分割。主要目标是提高伪标签质量的未标记的图像从未知的分布。为了实现它，我们执行傅立叶变换来学习跨域的低级统计信息，并增强图像以包含跨域信息。通过这些增强作为扰动，我们将输入馈送到置信度感知的交叉伪监督网络，以测量伪标签的方差，并正则化网络，以使用更自信的伪标签进行学习。我们的方法在公共数据集上创造了新的记录，即，M& M和SCGM。值得注意的是，在不使用域标签的情况下，我们的方法在具有2%标记数据的Dice on M&Ms数据集上甚至超过了使用域标签的现有技术11.67%。代码可在https://github.com/XMed-Lab/EPL_SemiDG上获得。
MICDIR: Multi-scale Inverse-consistent Deformable Image Registration using UNetMSS with Self-Constructing Graph Latent
Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）；Human Technopole（人类技术园）；German Centre for Neurodegenerative Disease（德国神经退行性疾病中心）；Centre for Behavioural Brain Sciences（行为脑科学中心）
JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
Nanjing University of Posts and Telecommunications（南京邮电大学）；Soochow University（苏州大学）；Kyushu Institute of Technology（九州工业大学）；Nanjing University of Science and Technology（南京理工大学）
