C2G-Net: Exploiting Morphological Properties for Image Classification
Center for Biomarker Research in Medicine GmbH（医学标志物研究中心有限公司）；Medical University of Graz（格拉茨医科大学）；Joanneum Research Forschungsgesellschaft mbH（约阿内研究有限公司）
Laurin Herbsthofer, Barbara Prietl, Martina Tomberger, Thomas Pieber, Pablo López-García
备注：
10 pages, 5 figures (Figure 3 with 4 sub-figures), Appendix A and Appendix B after the references. Originally submitted to ICML2020 but rejected
In this paper we propose C2G-Net, a pipeline for image classification that exploits the morphological properties of images containing a large number of similar objects like biological cells. C2G-Net consists of two components: (1) Cell2Grid, an image compression algorithm that identifies objects using segmentation and arranges them on a grid, and (2) DeepLNiNo, a CNN architecture with less than 10,000 trainable parameters aimed at facilitating model interpretability. To test the performance of C2G-Net we used multiplex immunohistochemistry images for predicting relapse risk in colon cancer. Compared to conventional CNN architectures trained on raw images, C2G-Net achieved similar prediction accuracy while training time was reduced by 85% and its model was is easier to interpret.
Deep Learning Hyperspectral Image Classification Using Multiple Class-based Denoising Autoencoders, Mixed Pixel Training Augmentation, and Morphological Operations
Max-C and Min-D Projection Autoassociative Fuzzy Morphological Memories: Theory and an Application for Face Recognition
Exact and Technological Science Center, Federal University of Recôncavo da Bahia（巴伊亚州联邦大学精确与技术科学中心）；Department of Applied Mathematics, University of Campinas（坎皮纳斯大学应用数学系）
Morphological Operation Residual Blocks: Enhancing 3D Morphological Feature Representation in Convolutional Neural Networks for Semantic Segmentation of Medical Images
Learning Deep Morphological Networks with Neural Architecture Search
ENSTA Paris, Institut Polytechnique de Paris（巴黎高等先进技术学院，巴黎理工学院）；Safrantech, Safran Group（赛峰技术公司，赛峰集团）；Mines ParisTech, PSL Research University（巴黎高等矿业学院，巴黎文理研究大学）；National University of Singapore（新加坡国立大学）
Slender Object Scene Segmentation in Remote Sensing Image Based on Learnable Morphological Skeleton with Segment Anything Model
School of Mathematical Sciences, Beijing Normal University（北京师范大学数学科学学院）；State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University（北京师范大学地理科学学部遥感科学国家重点实验室）
Travel Time Estimation without Road Networks: An Urban Morphological Layout Representation Approach
Ohio State University（俄亥俄州立大学）；University of California, Berkeley（加州大学伯克利分校）；Wisense AI（Wisense人工智能公司）
行程时间估计不仅是个人行程规划的重要任务，也是城市规划的重要任务。以前的方法侧重于对路段或子路径进行建模，然后总结最终预测，最近已被具有端到端训练的深度神经模型所取代。通常，这些方法是基于显式的特征表示，包括时空特征，交通状态等，在这里，我们认为，当地的交通状况是密切联系在一起的土地使用和建成环境，即，地铁站、主干道、交叉口、商业区、居民区等，但这种关系是时变的，过于复杂，无法明确有效地建模。因此，本文提出了一种端到端的多任务深度神经模型，名为Deep Image to Time（DeepI2T），主要从构建的环境图像中学习旅行时间，也就是说，形态布局图像，并在两个城市的真实世界数据集上展示新的最先进的性能。此外，我们的模型旨在解决路径感知和路径盲的情况下，在测试阶段。这项工作开辟了新的机会，使用公开的形态布局图像作为大量的信息，在多个地理相关的智慧城市应用。
Enforcing Morphological Information in Fully Convolutional Networks to Improve Cell Instance Segmentation in Fluorescence Microscopy Images
De Montfort University（德蒙福特大学）；Instituto de Investigación Biomédica de Málaga – IBIMA（马拉加生物医学研究所）；Costa Rica Institute of Technology（哥斯达黎加理工学院）；University of Costa Rica（哥斯达黎加大学）；Rovira i Virgili University（罗维拉-威尔吉利大学）；University of Malaga（马拉加大学）
