報告題目：Convex Shape Prior with Sublevel Set Representation and it’s Applications on CNN Image Segmentation
主 講 人：劉 君
騰 訊 ID：435 289 681
Convolutional Neural Networks (CNN) can well extract the features from natural images. However, the classification functions in the existing network architecture of CNNs are always simple and lack capabilities to handle important spatial information in a way that have been done for many well-known traditional variational models. Priors such as spatial regularization, object shapes and topology priors cannot be well handled by existing CNN architectures. We propose a novel Soft Threshold Dynamics (STD) based framework which can easily integrate many priors such as local and nonlocal image edges information, star/convexity shapes, topology priors (connectivity and holes) of the classic variational models into the DCNNs for image segmentation. The novelty of our method is to interpret the activation functions (including softmax, sigmoid, ReLU) as primal-dual variational problem, and thus many priors can be imposed in the dual space. By unrolling method, we can build several STD based network architectures which can enable the outputs of CNN to have many special priors. The proposed method is a general framework and it can be applied to any image segmentation CNNs. We will give some applications to show the efficiency of our method.
劉君，北京師范大學副教授，博士生導師。曾受邀訪問過美國UCLA、新加坡南洋理工、香港科技大學、香港浸會大學等高校。主要研究方向為變分法及深度學習相關的圖像處理算法與應用。一些研究結果發表在圖像處理與計算機視覺相關領域國際知名期刊如Int. J. Comput. Vis., IEEE T. Image. Process., IEEE T. Geosci. Remote, Pattern Recogn., SIAM J. Imaging Sci., J. Sci. Comput., J. Math. Imaging Vis. 等。研究成果曾獲教育部高等學校優秀科研成果二等獎（團體）, 北京市科技進步二等獎（團體）。主持參與多項國家科研項目。