Selective segmentation involves incorporating user input to partition an image into foreground and background, by discriminating between objects of a similar type. Typically, such methods involve introducing additional constraints to generic segmentation approaches. However, we show that this is often inconsistent with respect to common assumptions about the image. The proposed method introduces a new fitting term that is more useful in practice than the Chan-Vese framework. In particular, the idea is to define a term that allows for the background to consist of multiple regions of inhomogeneity. We provide comparitive experimental results to alternative approaches to demonstrate the advantages of the proposed method, broadening the possible application of these methods.
Active Mean Fields for Probabilistic Image Segmentation: Connections with Chan-Vese and Rudin-Osher-Fatemi Models
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；SRI International（SRI国际）；Stanford University（斯坦福大学）；Two Sigma Investments（Two Sigma投资公司）；Harvard Medical School（哈佛医学院）；Brigham and Women’s Hospital（布列根和妇女医院）
Variational multichannel multiclass segmentation using unsupervised lifting with CNNs
University of Innsbruck（因斯布鲁克大学）；VASCage GmbH（VASCage有限责任公司）；MRC-Laboratory of Molecular Biology（英国医学研究委员会分子生物学实验室）；Medical University of Innsbruck（因斯布鲁克医科大学）
GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks
CVLab, École Polytechnique Fédérale de Lausanne (EPFL)（瑞士联邦理工学院（EPFL）计算机视觉实验室）；Fudan University（复旦大学）；Beihang University（北航大学）；ELLIS Institute Finland（芬兰ELLIS研究所）；Aalto University（艾尔沃斯大学）；The Hong Kong Polytechnic University（香港理工大学）
