检索结果-南通市图书馆

A meaningful learning method for zero-shot Semantic Segmentation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第11期66卷 35-53页

作者： Xianglong LIU Shihao BAI Shan AN Shuo WANG Wei LIU Xiaowei ZHAO Yuqing MA State Key Lab of Software Development Environment Beihang University JD Health International Inc.

Zero-shot Semantic Segmentation, which is developed to segment unseen categories, has attracted increasing attention due to its strong practicability. Previous approaches usually applied semantic-visual mapping based on seen categories to unseen categories, and thus failed to generate meaningful unseen visual representations and struggled to balance the seen and unseen concepts in the classifier. To overcome the above limitations, we propose a novel meaningful learning method that could be embedded into any generationbased zero-shot Semantic Segmentation model, borrowing the idea from the educational psychology field. The proposed meaningful learning method refers to the process that the new concepts could be learned by relating to existing comprehensible concepts and harmoniously incorporated into the concept schema. Specifically, we introduce a generator with conjugate conceptual correlation(G3C) which generates meaningful unseen visual information through anchoring into existing concepts. Moreover, simulating the rational thinking mechanism,we introduce a fast-slow concept modulator to alleviate the noisy over-correlation problem introduced by G3C and further construct a comprehensive concept schema. Extensive experiments conducted on three benchmarks demonstrate the superior performance of our method, especially according to the commonlyacknowledged h-m Io U(e.g., 4% improvement on the Pascal-VOC dataset).

关键词： meaningful learning zero-shot learning Semantic Segmentation conjugate conceptual correlation fast-slow conceptual modulator

CrossFormer Embedding DeepLabv3+ for Remote Sensing Images Semantic Segmentation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 1353-1375页

作者： Qixiang Tong Zhipeng Zhu Min Zhang Kerui Cao Haihua Xing School of Information Science and Technology Hainan Normal UniversityHaikou571158China

High-resolution remote sensing image segmentation is a challenging task. In urban remote sensing, the presenceof occlusions and shadows often results in blurred or invisible object boundaries, thereby increasing the difficultyof segmentation. In this paper, an improved network with a cross-region self-attention mechanism for multi-scalefeatures based onDeepLabv3+is designed to address the difficulties of small object segmentation and blurred targetedge segmentation. First,we use CrossFormer as the backbone feature extraction network to achieve the interactionbetween large- and small-scale features, and establish self-attention associations between features at both large andsmall scales to capture global contextual feature information. Next, an improved atrous spatial pyramid poolingmodule is introduced to establish multi-scale feature maps with large- and small-scale feature associations, andattention vectors are added in the channel direction to enable adaptive adjustment of multi-scale channel features.The proposed networkmodel is validated using the PotsdamandVaihingen datasets. The experimental results showthat, compared with existing techniques, the network model designed in this paper can extract and fuse multiscaleinformation, more clearly extract edge information and small-scale information, and segment boundariesmore smoothly. Experimental results on public datasets demonstrate the superiority of ourmethod compared withseveral state-of-the-art networks.

关键词： Semantic Segmentation remote sensing multiscale self-attention

Augmented FCN: rethinking context modeling for Semantic Segmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第4期66卷 193-211页

作者： Dong ZHANG Liyan ZHANG Jinhui TANG School of Computer Science and Engineering Nanjing University of Science and Technology College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics

The effectiveness of modeling contextual information has been empirically shown in numerous computer vision tasks. In this paper, we propose a simple yet efficient augmented fully convolutional network(AugFCN) by aggregating content-and position-based object contexts for Semantic Segmentation.Specifically, motivated because each deep feature map is a global, class-wise representation of the input,we first propose an augmented nonlocal interaction(AugNI) to aggregate the global content-based contexts through all feature map interactions. Compared to classical position-wise approaches, AugNI is more efficient. Moreover, to eliminate permutation equivariance and maintain translation equivariance, a learnable,relative position embedding branch is then supportably installed in AugNI to capture the global positionbased contexts. AugFCN is built on a fully convolutional network as the backbone by deploying AugNI before the segmentation head network. Experimental results on two challenging benchmarks verify that AugFCN can achieve a competitive 45.38% mIoU(standard mean intersection over union) and 81.9% mIoU on the ADE20K val set and Cityscapes test set, respectively, with little computational overhead. Additionally, the results of the joint implementation of AugNI and existing context modeling schemes show that AugFCN leads to continuous segmentation improvements in state-of-the-art context modeling. We finally achieve a top performance of 45.43% mIoU on the ADE20K val set and 83.0% mIoU on the Cityscapes test set.

关键词： Semantic Segmentation context modeling long-range dependencies attention mechanism

Pyramid Bayesian Method for Model Uncertainty Evaluation of Semantic Segmentation in Autonomous Driving

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Automotive Innovation 2022年第1期5卷 70-78页

作者： Yang Zhao Wei Tian Hong Cheng School of Automation Engineering University of Electronic Science and Technology of ChinaChengduChina

With the fast-developing deep learning models in the field of autonomous driving,the research on the uncertainty estima-tion of deep learning models has also prevailed.Herein,a pyramid Bayesian deep learning method is proposed for the model uncertainty evaluation of Semantic Segmentation.Semantic Segmentation is one of the most important perception problems in understanding visual scene,which is critical for autonomous driving.This study to optimize Bayesian SegNet for uncertainty evaluation.This paper first simplifies the network structure of Bayesian SegNet by reducing the number of MC-Dropout layer and then introduces the pyramid pooling module to improve the performance of Bayesian SegNet.mIoU and mPAvPU are used as evaluation matrics to test the proposed method on the public Cityscapes dataset.The experimental results show that the proposed method improves the sampling effect of the Bayesian SegNet,shortens the sampling time,and improves the network performance.

关键词： Semantic Segmentation Bayesian SegNet Uncertainty Evaluation

Real-Time Semantic Segmentation via an Efficient Multi-Column Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2022年第6期37卷 1478-1491页

作者：彭程里马佳义 Electronic Information School Wuhan UniversityWuhan 430072China

Existing Semantic Segmentation networks based on the multi-column structure can hardly satisfy the efficiency and precision requirements simultaneously due to their shallow spatial branches.In this paper,we propose a new efficient multi-column network termed as LadderNet to address this problem.Our LadderNet includes two branches where the spatial branch generates high-resolution output feature map and the context branch encodes accurate semantic information.In particular,we first propose a channel attention fusion block and a global context module to enhance the information encoding ability of the context branch.Subsequently,a new branch fusion method,i.e.,fusing some middle feature maps of the context branch into the spatial branch,is developed to improve the depth of the spatial branch.Meanwhile,we design a feature fusing module to enhance the fusion quality of these two branches,leading to a more efficient network.We compare our model with other state-of-the-arts on PASCAL VOC 2012 and Cityscapes benchmarks.Experimental results demonstrate that,compared with other state-of-the-art methods,our LadderNet can achieve average 1.25%mIoU improvement with comparable or less computation.

关键词： Semantic Segmentation real time multi-column network deep learning

MFVNet: a deep adaptive fusion network with multiple field-of-views for remote sensing image Semantic Segmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第4期66卷 93-106页

作者： Yansheng LI Wei CHEN Xin HUANG Zhi GAO Siwei LI Tao HE Yongjun ZHANG School of Remote Sensing and Information Engineering Wuhan University

In recent years, the remote sensing image(RSI) Semantic Segmentation attracts increasing research interest due to its wide application. RSIs are difficult to be processed holistically on current GPU cards on account of their large field-of-views(FOVs). However, the prevailing practices such as downsampling and cropping will inevitably decrease the quality of Semantic Segmentation. To address this conflict,this paper proposes a new deep adaptive fusion network with multiple FOVs(MFVNet), which is specially designed for RSI Semantic Segmentation. Different from existing methods, MFVNet takes into consideration the differences among multiple FOVs. By pyramid sampling the RSI, we first obtain images on different scales with multiple FOVs. Images on the high scale with a large FOV can capture larger spatial contexts and complete object contours, while images on the low scale with a small FOV can keep the higher spatial resolution and more detailed information. Then scale-specific models are chosen to make the best predictions for all scales. Next, the output feature maps and score maps are aligned through the scale alignment module to overcome spatial misregistration among scales. Finally, the aligned score maps are fused with the help of adaptive weight maps generated by the adaptive fusion module, producing the fused prediction. The performance of MFVNet surpasses the previous state-of-the-art Semantic Segmentation models on three typical RSI datasets, demonstrating the effectiveness of the proposed MFVNet.

关键词： Semantic Segmentation remote sensing image (RSI) field-of-view (FOV) adaptive fusion convolutional neural network

Optimal CNN-based Semantic Segmentation model of cutting slope images

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2022年第4期16卷 414-433页

作者： Mansheng LIN Shuai TENG Gongfa CHEN Jianbing LV Zhongyu HAO School of Civil and Transportation Engineering Guangdong University of TechnologyGuangzhou 510006China JSTI Group Guangdong Inspection and Certification Co.Ltd Nanjing 210000China

This paper utilizes three popular Semantic Segmentation networks,specifically DeepLab v3+,fully convolutional network(FCN),and U-Net to qualitively analyze and identify the key components of cutting slope images in complex scenes and achieve rapid image-based slope detection.The elements of cutting slope images are divided into 7 categories.In order to determine the best algorithm for pixel level classification of cutting slope images,the networks are compared from three aspects:a)different neural networks,b)different feature extractors,and c)2 different optimization algorithms.It is found that DeepLab v3+with Resnet18 and Sgdm performs best,FCN 32s with Sgdm takes the second,and U-Net with Adam ranks third.This paper also analyzes the segmentation strategies of the three networks in terms of feature map visualization.Results show that the contour generated by DeepLab v3+(combined with Resnet18 and Sgdm)is closest to the ground truth,while the resulting contour of U-Net(combined with Adam)is closest to the input images.

关键词： slope damage image recognition Semantic Segmentation feature map visualizations

Semantic Segmentation by Using Down-Sampling and Subpixel Convolution: DSSC-UNet

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第4期75卷 683-696页

作者： Young-Man Kwon Sunghoon Bae Dong-Keun Chung Myung-Jae Lim Department of Medical IT Eulji University553Sanseong-daeroSujeong-guSeongnam-siGyeonggi-do13135Korea

Recently, Semantic Segmentation has been widely applied toimage processing, scene understanding, and many others. Especially, indeep learning-based Semantic Segmentation, the U-Net with convolutionalencoder-decoder architecture is a representative model which is proposed forimage segmentation in the biomedical field. It used max pooling operationfor reducing the size of image and making noise robust. However, instead ofreducing the complexity of the model, max pooling has the disadvantageof omitting some information about the image in reducing it. So, thispaper used two diagonal elements of down-sampling operation instead ofit. We think that the down-sampling feature maps have more informationintrinsically than max pooling feature maps because of keeping the Nyquisttheorem and extracting the latent information from them. In addition,this paper used two other diagonal elements for the skip connection. Indecoding, we used Subpixel Convolution rather than transposed convolutionto efficiently decode the encoded feature maps. Including all the ideas, thispaper proposed the new encoder-decoder model called Down-Sampling andSubpixel Convolution U-Net (DSSC-UNet). To prove the better performanceof the proposed model, this paper measured the performance of the UNetand DSSC-UNet on the Cityscapes. As a result, DSSC-UNet achieved89.6% Mean Intersection OverUnion (Mean-IoU) andU-Net achieved 85.6%Mean-IoU, confirming that DSSC-UNet achieved better performance.

关键词： Semantic Segmentation encoder-decoder U-Net DSSC-UNet subpixel convolution down-sampling

A Random Fusion of Mix 3D and Polar Mix to Improve Semantic Segmentation Performance in 3D Lidar Point Cloud

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第7期140卷 845-862页

作者： Bo Liu Li Feng Yufeng Chen School of Computer Science and Engineering Macao University of Science and TechnologyMacao999078China School of Computer Science and Artificial Intelligence Chaohu UniversityChaohu238000China Institute of Vehicle Information Control and Network Technology Hubei University of Automotive TechnologyShiyan442002China

This paper focuses on the effective utilization of data augmentation techniques for 3Dlidar point clouds to enhance the performance of neural network models.These point clouds,which represent spatial information through a collection of 3D coordinates,have found wide-ranging applications.Data augmentation has emerged as a potent solution to the challenges posed by limited labeled data and the need to enhance model generalization capabilities.Much of the existing research is devoted to crafting novel data augmentation methods specifically for 3D lidar point clouds.However,there has been a lack of focus on making the most of the numerous existing augmentation techniques.Addressing this deficiency,this research investigates the possibility of combining two fundamental data augmentation strategies.The paper introduces PolarMix andMix3D,two commonly employed augmentation techniques,and presents a new approach,named RandomFusion.Instead of using a fixed or predetermined combination of augmentation methods,RandomFusion randomly chooses one method from a pool of options for each instance or sample.This innovative data augmentation technique randomly augments each point in the point cloud with either PolarMix or Mix3D.The crux of this strategy is the random choice between PolarMix and Mix3Dfor the augmentation of each point within the point cloud data set.The results of the experiments conducted validate the efficacy of the RandomFusion strategy in enhancing the performance of neural network models for 3D lidar point cloud Semantic Segmentation tasks.This is achieved without compromising computational efficiency.By examining the potential of merging different augmentation techniques,the research contributes significantly to a more comprehensive understanding of how to utilize existing augmentation methods for 3D lidar point clouds.RandomFusion data augmentation technique offers a simple yet effective method to leverage the diversity of augmentation techniques and boost the robustness of models.The insights gained from this

关键词： 3D lidar point cloud data augmentation RandomFusion Semantic Segmentation