Learning Invariant Inter-pixel Correlations for Superpixel Generation
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Beijing Key Laboratory of Advanced Information Science and Network Technology（北京市高级信息科学与网络技术重点实验室）；Frontiers Science Center for Smart High-speed Railway System, Beijing Jiaotong University（北京交通大学智慧高铁系统前沿科学中心）；DaoAI Robotics Inc.（道智机器人公司）
Deep superpixel algorithms have made remarkable strides by substituting hand-crafted features with learnable ones. Nevertheless, we observe that existing deep superpixel methods, serving as mid-level representation operations, remain sensitive to the statistical properties (e.g., color distribution, high-level semantics) embedded within the training dataset. Consequently, learnable features exhibit constrained discriminative capability, resulting in unsatisfactory pixel grouping performance, particularly in untrainable application scenarios. To address this issue, we propose the Content Disentangle Superpixel (CDS) algorithm to selectively separate the invariant inter-pixel correlations and statistical properties, i.e., style noise. Specifically, We first construct auxiliary modalities that are homologous to the original RGB image but have substantial stylistic variations. Then, driven by mutual information, we propose the local-grid correlation alignment across modalities to reduce the distribution discrepancy of adaptively selected features and learn invariant inter-pixel correlations. Afterwards, we perform global-style mutual information minimization to enforce the separation of invariant content and train data styles. The experimental results on four benchmark datasets demonstrate the superiority of our approach to existing state-of-the-art methods, regarding boundary adherence, generalization, and efficiency. Code and pre-trained model are available at https://github.com/rookiie/CDSpixel.
STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detection
School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；Yunnan Key Laboratory of Service Computing, Yunnan University of Finance and Economics（云南财经大学服务计算重点实验室）；Innovation Academy for Microsatellites of Chinese Academy of Science（中国科学院微卫星创新院）；Institute for Urban Governance, Shanghai University（上海大学城市治理研究院）
过分割成超像素是一个重要的预处理步骤，可以巧妙地压缩输入大小并加速更高级别的任务。传统上，超像素被认为是一小簇基于正方形的像素，这些像素具有相似的颜色强度并且彼此靠近。在这种离散模型中，超像素的边界通常具有不规则的锯齿形，由给定像素网格的水平或垂直边缘组成。然而，数字图像表示一个连续的世界，因此以下的连续模型在分辨率无关的公式可以更适合于重建问题。与网格中的正方形不同，分辨率无关的超像素被定义为具有直边的多边形，该直边在子像素分辨率下具有任何可能的斜率。过分割问题的更难的连续版本是将图像分割成多边形，并找到每个多边形的最佳（例如，恒定）颜色，以便产生的彩色网格很好地近似给定的图像。这样的多边形网格可以以任何更高的分辨率渲染，所有边缘都保持笔直。我们提出了一个快速转换的任何传统的超像素到多边形，并保证其直边不相交。将基于超像素SEEDS（Superpixels Extracted via Energy-Driven Sampling）和SLIC（Simple Linear Iterative Clustering）的网格与过去基于线段检测器的网格进行了比较。在伯克利分割数据库上的实验证实，新的超像素比基于像素的超像素具有更紧凑的形状。
Nankai International Advanced Research Institute（南开大学国际高等研究院）；Peng Cheng Laboratory（鹏城实验室）；College of Computer Science, Nankai University（南开大学计算机学院）；University of Science and Technology Beijing（北京科技大学）；University of Macau（澳门大学）
Superpixel Segmentation Based on Spatially Constrained Subspace Clustering
Huazhong University of Science and Technology（华中科技大学）；City University of Hong Kong（香港城市大学）；Southeast University（东南大学）；Beijing Jiaotong University（北京交通大学）
Superpixel-Based Background Recovery from Multiple Images
Friedrich-Alexander University Erlangen-Nuremberg（弗里德里希-亚历山大大学埃尔兰根-纽伦堡分校）；Erlangen Graduate School in Advanced Optical Technologies (SAOT)（埃尔兰根先进光学技术研究生院（SAOT））
Two-Phase Object-Based Deep Learning for Multi-temporal SAR Image Change Detection
College of Microelectronics and Communication Engineering, Chongqing University（重庆大学微电子与通信工程学院）；Chongqing Key Laboratory of Space Information Network and Intelligent Information Fusion（重庆空间信息网络与智能信息融合重点实验室）；Lancaster Environment Centre, Lancaster University（兰卡斯特大学兰卡斯特环境中心）；UK Centre for Ecology & Hydrology（英国生态与水文中心）
Stereo Superpixel Segmentation Via Decoupled Dynamic Spatial-Embedding Fusion Network
Hainan University（海南大学）；Wuhan University of Technology（武汉理工大学）；Beijing Jiaotong University（北京交通大学）；Shenzhen University（深圳大学）；City University of Hong Kong（香港城市大学）；City University of Hong Kong Shenzhen Research Institute（香港城市大学深圳研究院）
Learning the Superpixel in a Non-iterative and Lifelong Manner
Institute of Medical Technology Peking University Health Science Center Peking University（北京大学医学部医学技术研究院）；Bytedance AI Lab（字节跳动人工智能实验室）；Department of Biomedical Engineering Peking University（北京大学生物医学工程系）；Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Biomedical Engineering Peking University Shenzhen Graduate School（北京大学深圳研究生院生物医学工程研究所）
Unsupervised Skin Lesion Segmentation via Structural Entropy Minimization on Multi-Scale Superpixel Graphs
Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Salesforce AI Research（赛富时人工智能研究院）；Didi Chuxing（滴滴出行）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Lehigh University（理海大学）
SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-training
Institute of Medical Technology, Peking University Health Science Center, Peking University（北京大学医学部医学技术研究所）；Department of Biomedical Engineering, Peking University（北京大学生物医学工程系）；National Biomedical Imaging Center, Peking University（北京大学国家生物医学成像中心）；Institute of Biomedical Engineering, Shenzhen Bay Laboratory（深圳湾实验室生物医学工程研究所）；Institute of Biomedical Engineering, Peking University Shenzhen Graduate School（北京大学深圳研究生院生物医学工程研究所）
Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images
School of Software Engineering, Southeast University（东南大学软件学院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及交叉应用关键实验室（东南大学））；Department of Computing and Information Sciences, Saint Francis University（圣弗朗西斯大学计算机与信息科学系）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
Superpixel-Based QUBO for Scalable Quantum-Enhanced Medical Image Segmentation
American University of Beirut（贝鲁特美国大学）；Centre de Visió per Computador (CVC)（计算机视觉中心 (CVC)）；Ingenii Inc.（英格尼公司）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution
Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China（华南理工大学谢民武智能工程学院）；Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR（香港理工大学电子与电气工程系）；College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou, China（福建师范大学光电工程学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China（南京理工大学计算机科学与工程学院）；School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China（中山大学计算机科学与工程学院）
