arXiv 2103.089142021-03-16cs.CV

EADNet: Efficient Asymmetric Dilated Network for Semantic Segmentation

Fudan University（复旦大学）；Shanghai Huawei Technologies Co., Ltd.（上海华为技术有限公司）

Qihang Yang, Tao Chen, Jiayuan Fan, Ye Lu, Chongyan Zuo, Qinghua Chi

英文摘要：

Due to real-time image semantic segmentation needs on power constrained edge devices, there has been an increasing desire to design lightweight semantic segmentation neural network, to simultaneously reduce computational cost and increase inference speed. In this paper, we propose an efficient asymmetric dilated semantic segmentation network, named EADNet, which consists of multiple developed asymmetric convolution branches with different dilation rates to capture the variable shapes and scales information of an image. Specially, a multi-scale multi-shape receptive field convolution (MMRFC) block with only a few parameters is designed to capture such information. Experimental results on the Cityscapes dataset demonstrate that our proposed EADNet achieves segmentation mIoU of 67.1 with smallest number of parameters (only 0.35M) among mainstream lightweight semantic segmentation networks.

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

C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation

Seoul National University（首尔国立大学）；CLOVA AI Research, Naver Corp.（Naver公司CLOVA人工智能研究院）

One of the practical choices for making a lightweight semantic segmentation model is to combine a depth-wise separable convolution with a dilated convolution. However, the simple combination of these two methods results in an over-simplified operation which causes severe performance degradation due to loss of information contained in the feature map. To resolve this problem, we propose a new block called Concentrated-Comprehensive Convolution (C3) which applies the asymmetric convolutions before the depth-wise separable dilated convolution to compensate for the information loss due to dilated …

2019-07-28cs.CV

DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation

Sungkyunkwan University（成均馆大学）

As a pixel-level prediction task, semantic segmentation needs large computational cost with enormous parameters to obtain high performance. Recently, due to the increasing demand for autonomous systems and robots, it is significant to make a tradeoff between accuracy and inference speed. In this paper, we propose a novel Depthwise Asymmetric Bottleneck (DAB) module to address this dilemma, which efficiently adopts depth-wise asymmetric convolution and dilated convolution to build a bottleneck structure. Based on the DAB module, we design a Depth-wise Asymmetric Bottleneck Network (DABNet) espe…

2019-10-01cs.CV

Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation

National Chiao Tung University（国立交通大学）；Industrial Technology Research Institute（工业技术研究院）

Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most semantic segmentation research focuses on improving estimation accuracy with little consideration on efficiency. Several previous studies that emphasize high-speed inference often fail to produce high-accuracy segmentation results. In this paper, we propose a novel convolutional network named Efficient Dense modules with Asymmetric convolution (EDANet), which employs an asymmetric convolution structure and incorporates dilated convolution and dense connectivity to achieve hig…

2019-12-28cs.CV

A De-raining semantic segmentation network for real-time foreground segmentation

Zhejiang University（浙江大学）；Henan University of Science and Technology（河南科技大学）

Few researches have been proposed specifically for real-time semantic segmentation in rainy environments. However, the demand in this area is huge and it is challenging for lightweight networks. Therefore, this paper proposes a lightweight network which is specially designed for the foreground segmentation in rainy environments, named De-raining Semantic Segmentation Network (DRSNet). By analyzing the characteristics of raindrops, the MultiScaleSE Block is targetedly designed to encode the input image, it uses multi-scale dilated convolutions to increase the receptive field, and SE attention m…

2021-04-16cs.CV

JetSeg：面向低功耗GPU嵌入式系统的高效实时语义分割模型

JetSeg: Efficient Real-Time Semantic Segmentation Model for Low-Power GPU-Embedded Systems

Instituto Politécnico Nacional（国立理工学院）；CITEDI-IPN（CITEDI-国立理工学院）

提出面向低功耗GPU嵌入式系统的实时语义分割模型JetSeg，通过JetNet编码器、JetBlock模块、JetConv策略和JetLoss损失函数，在减少参数和计算量的同时显著提升推理速度。

2023-05-19cs.AIcs.CVcs.LG

基于混合卷积与交互融合的精准伪装目标检测

Towards Accurate Camouflaged Object Detection with Mixture Convolution and Interactive Fusion

National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University（西北工业大学计算机学院）；Center for Brain Imaging Science and Technology, Zhejiang University（浙江大学）；School of Computer Science, China University of Geosciences（中国地质大学计算机学院）；Optical Electrical and Computer Engineering, University of Shanghai for Science and Technology（上海理工大学）；School of Electrical Engineering & Information Department, Northeast Petroleum University（东北石油大学）；School of Electronic, Electrical Engineering and Physics, Fujian University of Technology（福建工程学院）

本文提出一种融合大感受野与有效特征融合的深度学习伪装目标检测方法，通过双分支混合卷积和交互融合模块，在基准数据集上优于现有最先进方法。

2024-07-19cs.CV

更多相关论文收起更多论文

PreCM：用于语义分割的基于填充的旋转等变卷积模式

PreCM: The Padding-based Rotation Equivariant Convolution Mode for Semantic Segmentation

Shanghai Key Laboratory of Intelligent Sensing and Recognition, School of Sensing Science and Engineering, Shanghai Jiao Tong University（上海智能感知与识别重点实验室，传感科学与工程学院，上海交通大学）；Intelligent Photoelectric Sensing Institute, School of Sensing Science and Engineering, Shanghai Jiao Tong University（智能光电传感研究院，传感科学与工程学院，上海交通大学）

本文提出了一种基于填充的旋转等变卷积模式PreCM及旋转差异评估指标，使网络具备抵抗方向干扰的旋转等变性，在多数据集上显著提升了六种语义分割网络在随机旋转下的平均IOU并降低了RD值。

2025-04-30cs.CV

Pathological OCT Retinal Layer Segmentation using Branch Residual U-shape Networks

University of Bern（伯尔尼大学）；RetinAI Medical GmbH（RetinAI Medical 公司）；Bern University Hospital（伯尔尼大学医院）

The automatic segmentation of retinal layer structures enables clinically-relevant quantification and monitoring of eye disorders over time in OCT imaging. Eyes with late-stage diseases are particularly challenging to segment, as their shape is highly warped due to pathological biomarkers. In this context, we propose a novel fully Convolutional Neural Network (CNN) architecture which combines dilated residual blocks in an asymmetric U-shape configuration, and can segment multiple layers of highly pathological eyes in one shot. We validate our approach on a dataset of late-stage AMD patients an…

2017-07-16cs.CV

联合多尺度门控变换器和先验引导卷积网络用于学习图像压缩

Joint Multi-scale Gated Transformer and Prior-guided Convolutional Network for Learned Image Compression

College of Electronics and Information Engineering, Sichuan University（电子信息工程学院，四川大学）

本文提出了一种联合多尺度门控变换器和先验引导卷积网络，用于提升学习图像压缩的性能与效率。

2025-11-30cs.CV

Efficient 3D Fully Convolutional Networks for Pulmonary Lobe Segmentation in CT Images

University of Oxford（牛津大学）；Universiti Malaysia Perlis（马来西亚玻璃市大学）；Churchill Hospital（丘吉尔医院）

The human lung is a complex respiratory organ, consisting of five distinct anatomic compartments called lobes. Accurate and automatic segmentation of these pulmonary lobes from computed tomography (CT) images is of clinical importance for lung disease assessment and treatment planning. However, this task is challenging due to ambiguous lobar boundaries, anatomical variations and pathological deformations. In this paper, we propose a high-resolution and efficient 3D fully convolutional network to automatically segment the lobes. We refer to the network as Pulmonary Lobe Segmentation Network (PL…

2019-09-16cs.CVeess.IV