Instance segmentation is one of the actively studied research topics in computer vision in which many objects of interest should be separated individually. While many feed-forward networks produce high-quality segmentation on different types of images, their results often suffer from topological errors (merging or splitting) for segmentation of many objects, requiring post-processing. Existing iterative methods, on the other hand, extract a single object at a time using discriminative knowledge-based properties (shapes, boundaries, etc.) without relying on post-processing, but they do not scale well. To exploit the advantages of conventional single-object-per-step segmentation methods without impairing the scalability, we propose a novel iterative deep reinforcement learning agent that learns how to differentiate multiple objects in parallel. Our reward function for the trainable agent is designed to favor grouping pixels belonging to the same object using a graph coloring algorithm. We demonstrate that the proposed method can efficiently perform instance segmentation of many objects without heavy post-processing.
Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring
Shanghai Academy of Artificial Intelligence for Science（上海人工智能科学研究院）；Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；School of Life Sciences and Biotechnology, Shanghai Jiao Tong University（上海交通大学生命科学与生物技术学院）；Lingang Laboratory（临港实验室）；Renji Hospital, School of Medicine, Shanghai Jiao Tong University（仁济医院，上海交通大学医学院）
Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Information Engineering, Huzhou Normal University（湖州师范学院信息工程学院）；School of Artificial Intelligence, Nanjing University of Posts and Telecommunications（南京邮电大学人工智能学院）；National Key Laboratory of Tibetan Language Intelligence（藏语智能国家重点实验室）；Zhejiang University（浙江大学）；Beijing Normal University（北京师范大学）
Learning to Cluster for Proposal-Free Instance Segmentation
Georgia Institute of Technology（佐治亚理工学院）；University of Maryland College Park（马里兰大学帕克分校）；Georgia Tech Research Institute（佐治亚理工学院研究院）；Honda Research Institute（本田研究所）
Automatic ply-specific analyses of CFRP micrographs using shortest-path-based ply distinction
German Aerospace Center (DLR)（德国航空航天中心（DLR））；Institute of Lightweight Systems（轻质系统研究所）；Composite Process Technologies（复合材料加工技术）；Institute of Analysis and Algebra（分析与代数研究所）
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation
Faculty of Electrical Engineering and Computing, University of Zagreb（萨格勒布大学电气工程与计算学院）；Faculty of Computer and Information Science, University of Ljubljana（卢布尔雅那大学计算机与信息科学学院）；Fundamental AI Lab, University of Technology Nuremberg（纽伦堡工业大学基础人工智能实验室）
Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving
Harvard University（哈佛大学）；Columbia University（哥伦比亚大学）；China University of Mining and Technology（中国矿业大学）；University of California Berkeley（加州大学伯克利分校）；Carnegie Mellon University（卡内基梅隆大学）；The Hong Kong Polytechnic University（香港理工大学）
