首页/论文/1902.07476

arXiv 1902.074762019-04-03cs.CV

An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions

University of Oulu（奥卢大学）

Sercan Türkmen, Janne Heikkilä

备注：: 12 pages, 6 figures, 5 tables
DOI：: 10.1007/978-3-030-20205-7_4

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Assigning a label to each pixel in an image, namely semantic segmentation, has been an important task in computer vision, and has applications in autonomous driving, robotic navigation, localization, and scene understanding. Fully convolutional neural networks have proved to be a successful solution for the task over the years but most of the work being done focuses primarily on accuracy. In this paper, we present a computationally efficient approach to semantic segmentation, while achieving a high mean intersection over union (mIOU), 70.33% on Cityscapes challenge. The network proposed is capable of running real-time on mobile devices. In addition, we make our code and model weights publicly available.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Google Inc.（谷歌公司）

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effecti…

2018-08-22cs.CV

用于改进农业语义分割的双空洞可分离卷积

Dual Atrous Separable Convolution for Improving Agricultural Semantic Segmentation

Electrical and Computer. Engg.（电气与计算机工程系）；Software Engg.（软件工程系）；Applied Science University of Alabama Huntsville（阿拉巴马大学亨茨维尔应用科学学院）

本研究提出一种基于DeepLabV3框架并集成双空洞可分离卷积模块的轻量级图像分割方法，通过优化膨胀率与跳跃连接，在Agriculture Vision数据集上以更低复杂度实现媲美SOTA模型的性能。

2025-06-27cs.CV

DAS-SK：一种集成双空洞分离和选择性核的自适应模型用于农业语义分割

DAS-SK: An Adaptive Model Integrating Dual Atrous Separable and Selective Kernel CNN for Agriculture Semantic Segmentation

Electrical & Computer Engineering Department of Lakehead University（拉夫莱德大学电气与计算机工程系）；Faculty of Software Engineering of Lakehead University（拉夫莱德大学软件工程系）；Faculty of Applied Science of the University of Alabama（阿拉巴马大学应用科学系）；School of Computer Science Engineering and Information Systems, Vellore Institute of Technology（维洛雷理工学院计算机科学工程与信息系统学院）

DAS-SK通过集成双空洞分离和选择性核卷积，实现高效农业语义分割，优于现有模型。

2026-02-09cs.CV

LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation

Ain Shams University（艾因夏姆斯大学）

Semantic image segmentation plays a pivotal role in many vision applications including autonomous driving and medical image analysis. Most of the former approaches move towards enhancing the performance in terms of accuracy with a little awareness of computational efficiency. In this paper, we introduce LiteSeg, a lightweight architecture for semantic image segmentation. In this work, we explore a new deeper version of Atrous Spatial Pyramid Pooling module (ASPP) and apply short and long residual connections, and depthwise separable convolution, resulting in a faster and efficient model. LiteS…

2019-12-13cs.CV

LSNet: Extremely Light-Weight Siamese Network For Change Detection in Remote Sensing Image

University of Electronic Science and Technology of China（电子科技大学）；Truly Opto-Electronics Co., Ltd.（信利光电股份有限公司）

The Siamese network is becoming the mainstream in change detection of remote sensing images (RSI). However, in recent years, the development of more complicated structure, module and training processe has resulted in the cumbersome model, which hampers their application in large-scale RSI processing. To this end, this paper proposes an extremely lightweight Siamese network (LSNet) for RSI change detection, which replaces standard convolution with depthwise separable atrous convolution, and removes redundant dense connections, retaining only valid feature flows while performing Siamese feature …

2022-01-23cs.CV

AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks

Samsung SOC R&D Lab（三星SOC研发实验室）

In this paper, a new deep learning architecture for stereo disparity estimation is proposed. The proposed atrous multiscale network (AMNet) adopts an efficient feature extractor with depthwise-separable convolutions and an extended cost volume that deploys novel stereo matching costs on the deep features. A stacked atrous multiscale network is proposed to aggregate rich multiscale contextual information from the cost volume which allows for estimating the disparity with high accuracy at multiple scales. AMNet can be further modified to be a foreground-background aware network, FBA-AMNet, which…

2019-04-19cs.CV

更多相关论文收起更多论文

融合密集深度可分离空洞空间金字塔池化与DeepLabV3+的卫星影像道路自动提取

Automated Road Extraction from Satellite Imagery Integrating Dense Depthwise Dilated Separable Spatial Pyramid Pooling with DeepLabV3+

Knight Foundation School of Computing and Information Sciences（奈特基金会计算与信息科学学院）；Florida International University（佛罗里达国际大学）

本文提出用密集深度可分离空洞空间金字塔池化模块替代DeepLabV3+中的ASPP，并结合主干网络与Squeeze-and-Excitation模块，以提升卫星影像中复杂道路结构的自动提取精度。

2024-10-18cs.CVcs.LG

ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

University of Washington（华盛顿大学）；Allen Institute for AI (AI2)（艾伦人工智能研究所（AI2））

We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise dilated separable convolutions to learn representations from a large effective receptive field with fewer FLOPs and parameters. The performance of our network is evaluated on four different tasks: (1) object classification, (2) semantic segmentation, (3) object detection, and (4) language modeling. Experiments on these tasks, including image classification on the ImageNet and language modeling on the …

2019-03-30cs.CV

高效卷积神经网络中用于加速可分离卷积的深度分解

Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks

Carnegie Mellon University（卡内基梅隆大学）；Columbia University（哥伦比亚大学）；Michigan State University（密歇根州立大学）

针对深度可分离卷积加速但损失准确率的问题，提出基于SVD/GSVD的深度分解，将常规卷积分解为可分离卷积，并在ShuffleNet V2上验证其优于通道分解且Top-1提升约2%。

2023-09-23cs.CV

Pelee: A Real-Time Object Detection System on Mobile Devices

University of Western Ontario（西安大略大学）

An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed in recent years, for example, MobileNet, ShuffleNet, and MobileNetV2. However, all these models are heavily dependent on depthwise separable convolution which lacks efficient implementation in most deep learning frameworks. In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead. On ImageNet IL…

2019-01-18cs.CV

DiCENet: Dimension-wise Convolutions for Efficient Networks

University of Washington（华盛顿大学）

We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion. The dimension-wise convolutions apply light-weight convolutional filtering across each dimension of the input tensor while dimension-wise fusion efficiently combines these dimension-wise representations; allowing the DiCE unit to efficiently encode spatial and channel-wise information contained in the input tensor. The DiCE unit is simple and can be seamlessly integrated with any architecture to improve its efficiency and performance. Compared to depth-wise…

2020-11-30cs.CVcs.LGeess.IV

通道注意力可分离卷积网络用于皮肤病变分割

Channel Attention Separable Convolution Network for Skin Lesion Segmentation

Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Weifang University（潍坊学院）；Jiangxi Normal University（江西师范大学）

针对皮肤病变分割的准确性和自动化需求，提出通道注意力可分离卷积网络（CASCN），在PH2数据集上以0.9461的Dice系数和0.9645的准确率实现最先进性能。

2023-09-03cs.CVeess.IV

Opto-UNet: Optimized UNet for Segmentation of Varicose Veins in Optical Coherence Tomography

Human veins are important for carrying the blood from the body-parts to the heart. The improper functioning of the human veins may arise from several venous diseases. Varicose vein is one such disease wherein back flow of blood can occur, often resulting in increased venous pressure or restricted blood flow due to changes in the structure of vein. To examine the functional characteristics of the varicose vein, it is crucial to study the physical and bio mechanical properties of the vein. This work proposes a segmentation model Opto-UNet, for segmenting the venous wall structure. Optical Cohere…

2023-03-20cs.CVcs.LGeess.IV

Res-CR-Net, a residual network with a novel architecture optimized for the semantic segmentation of microscopy images

Wayne State University（韦恩州立大学）；NanoBioScience Institute（纳米生物科学研究所）；College of Engineering（工学院）；School of Medicine（医学院）；Center for Molecular Medicine & Genetics（分子医学与遗传学中心）；University of Vermont College of Medicine（佛蒙特大学医学院）；Karolinska Institute（卡罗林斯卡学院）

Deep Neural Networks (DNN) have been widely used to carry out segmentation tasks in both electron and light microscopy. Most DNNs developed for this purpose are based on some variation of the encoder-decoder type U-Net architecture, in combination with residual blocks to increase ease of training and resilience to gradient degradation. Here we introduce Res-CR-Net, a type of DNN that features residual blocks with either a bundle of separable atrous convolutions with different dilation rates or a convolutional LSTM. The number of filters used in each residual block and the number of blocks are …

2020-04-14cs.CVcs.LGeess.IV