Previous deep learning-based line segment detection (LSD) suffers from the immense model size and high computational cost for line prediction. This constrains them from real-time inference on computationally restricted environments. In this paper, we propose a real-time and light-weight line segment detector for resource-constrained environments named Mobile LSD (M-LSD). We design an extremely efficient LSD architecture by minimizing the backbone network and removing the typical multi-module process for line prediction found in previous methods. To maintain competitive performance with a light-weight network, we present novel training schemes: Segments of Line segment (SoL) augmentation, matching and geometric loss. SoL augmentation splits a line segment into multiple subparts, which are used to provide auxiliary line data during the training process. Moreover, the matching and geometric loss allow a model to capture additional geometric cues. Compared with TP-LSD-Lite, previously the best real-time LSD method, our model (M-LSD-tiny) achieves competitive performance with 2.5% of model size and an increase of 130.5% in inference speed on GPU. Furthermore, our model runs at 56.8 FPS and 48.6 FPS on the latest Android and iPhone mobile devices, respectively. To the best of our knowledge, this is the first real-time deep LSD available on mobile devices. Our code is available.
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization
Tencent AI Lab(腾讯人工智能实验室);Tencent Data Platform(腾讯数据平台部);Tsinghua University(清华大学);Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);Peng Cheng Lab(鹏城实验室)
Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation
DAMO Academy, Alibaba Group(阿里巴巴达摩院);State University of New York at Stony Brook(纽约州立大学石溪分校);Johns Hopkins University(约翰斯·霍普金斯大学);The First Affiliated Hospital Zhejiang University(浙江大学医学院附属第一医院)
Light-weight Retinal Layer Segmentation with Global Reasoning
School of Mechanical Engineering, Shandong University(山东大学机械工程学院);Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR)(山东大学-南洋理工大学人工智能联合研究中心);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会)
CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation
George Washington University(乔治华盛顿大学)
目前,深度学习技术的发展正在提供识别、分类和量化医学图像中的模式的工具。分割是医学图像分析的重要应用之一。在这方面,U-Net是医学图像分割任务的主要方法。然而,我们发现这些基于U-Net的模型在很多方面都有局限性,例如,U-Net中数以百万计的参数消耗了大量的计算资源和内存,缺乏全局信息,以及遗漏了一些棘手的对象。因此,我们应用两个修改来改进U-Net模型:1)设计并添加了扩张的通道式CNN模块,2)简化了U形网络。在此基础上,提出了一种新的轻量级结构--医学特征金字塔网络(CFPNet-M)。为了评估我们的方法,我们选择了五个不同模式的数据集:热成像,电子显微镜,内窥镜,皮肤镜和数字视网膜图像。并与几种不同参数尺度的模型进行了性能比较。本文还介绍了我们以前对DC-UNet和一些常用的轻量级神经网络的研究。我们应用谷本相似性,而不是Jaccard指数的灰度图像测量。相比之下,CFPNet-M在所有五个医学数据集上实现了相当的分割结果,仅使用了65万个参数,约为U-Net的2%,内存为8.8 MB。同时,在单个RTX 2070 Ti GPU上,推理速度可以达到80 FPS,输入大小为256 x 192像素。
LM-Net: A Light-weight and Multi-scale Network for Medical Image Segmentation
College of Electronic Information, Guangxi Minzu University(广西民族大学电子信息学院);The First Affiliated Hospital of Sun Yat-Sen University(中山大学附属第一医院);School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University(西北工业大学人工智能、光学与电子学院(iOPEN))
NimbleReg: A light-weight deep-learning framework for diffeomorphic image registration
Hawkes Institute \& Department of Computer Science, University College London, London, UK AINOSTICS ltd., Manchester, UK ESIR, Universit\'e de Rennes, Rennes, France
Cell segmentation from telecentric bright-field transmitted light microscopy images using a Residual Attention U-Net: a case study on HeLa line
University of South Bohemia in České Budějovice(捷克布杰约维采南波希米亚大学);Helmholtz Centre Potsdam GFZ German Research Centre for Geosciences(亥姆霍兹波茨坦中心德国地球科学研究中心)