检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

8,902 篇 会议
42 篇 期刊文献
18 册 图书

馆藏范围

8,961 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

4,560 篇 工学
- 4,019 篇 计算机科学与技术...
- 2,178 篇 软件工程
- 1,242 篇 光学工程
- 555 篇 控制科学与工程
- 431 篇 信息与通信工程
- 429 篇 机械工程
- 294 篇 电气工程
- 287 篇 仪器科学与技术
- 179 篇 生物工程
- 159 篇 生物医学工程（可授...
- 119 篇 电子科学与技术（可...
- 61 篇 安全科学与工程
- 58 篇 建筑学
- 58 篇 化学工程与技术
- 52 篇 土木工程
- 49 篇 交通运输工程
- 40 篇 力学（可授工学、理...
2,065 篇 理学
- 1,382 篇 物理学
- 1,198 篇 数学
- 420 篇 统计学（可授理学、...
- 238 篇 生物学
- 54 篇 化学
- 36 篇 系统科学
263 篇 管理学
- 180 篇 图书情报与档案管...
- 89 篇 管理科学与工程(可...
- 47 篇 工商管理
222 篇 医学
- 221 篇 临床医学
- 39 篇 基础医学(可授医学...
205 篇 艺术学
- 205 篇 设计学（可授艺术学...
45 篇 法学
- 43 篇 社会学
21 篇 农学
14 篇 教育学
9 篇 经济学
6 篇 军事学

主题

3,413 篇 computer vision
1,216 篇 pattern recognit...
946 篇 cameras
908 篇 conferences
765 篇 computer science
674 篇 image segmentati...
618 篇 layout
598 篇 training
548 篇 shape
518 篇 robustness
451 篇 feature extracti...
448 篇 humans
445 篇 face recognition
405 篇 computational mo...
402 篇 object detection
365 篇 visualization
356 篇 computer archite...
336 篇 application soft...
304 篇 lighting
258 篇 image reconstruc...

机构

41 篇 microsoft resear...
30 篇 department of co...
25 篇 department of co...
23 篇 institute for co...
22 篇 department of co...
22 篇 school of comput...
20 篇 university of sc...
20 篇 swiss fed inst t...
19 篇 tsinghua univers...
19 篇 institute of com...
18 篇 swiss fed inst t...
17 篇 the robotics ins...
17 篇 carnegie mellon ...
17 篇 computer vision ...
17 篇 department of co...
16 篇 institute of inf...
16 篇 school of comput...
15 篇 school of comput...
15 篇 carnegie mellon ...
14 篇 national laborat...

作者

57 篇 timofte radu
25 篇 huang thomas s.
24 篇 van gool luc
23 篇 s.k. nayar
22 篇 nayar shree k.
22 篇 t. kanade
21 篇 jain anil k.
20 篇 luc van gool
19 篇 t.s. huang
18 篇 xiaoou tang
18 篇 murino vittorio
18 篇 horst bischof
17 篇 a.k. jain
17 篇 t. darrell
16 篇 g. healey
16 篇 bowyer kevin w.
16 篇 bischof horst
15 篇 m.j. black
15 篇 li stan z.
15 篇 m. shah

语言

8,913 篇 英文
40 篇 其他
8 篇 中文
1 篇 土耳其文

检索条件"任意字段=IEEE-Computer-Society Conference on Computer Vision and Pattern Recognition Workshops"

共 8962 条记录，以下是1741-1750 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Investigating Spatially Correlated patterns in Adversarial Images 31

Investigating Spatially Correlated Patterns in Adversarial I...

引用

31st ieee International conference on Image Processing Challenges and workshops, ICIPCW 2024

作者： Chattopadhyay, Nandish Zhi, Lionell Yip En Xing, Bryan Tan Chattopadhyay, Anupam Shafique, Muhammad Abu Dhabi United Arab Emirates Nanyang Technological University School of Computer Science and Engineering Singapore

ISBN: (纸本)9798331515942

Adversarial attacks have proved to be the major impediment in the progress on research towards reliable machine learning solutions. Carefully crafted perturbations, imperceptible to human vision, can be added to images to force misclassification by an otherwise high performing neural network. To have a better understanding of the key contributors of such structured attacks, we searched for and studied spatially co-located patterns in the distribution of pixels in the input space. In this paper, we propose a framework for segregating and isolating regions within an input image which are particularly critical towards either classification (during inference), or adversarial vulnerability or both. We assert that during inference, the trained model looks at a specific region in the image, which we call Region of Importance (RoI);and the attacker looks at a region to alter/modify, which we call Region of Attack (RoA). The success of this approach could also be used to design a post-hoc adversarial defence method, as illustrated by our observations. This uses the notion of blocking out (we call neutralizing) that region of the image which is highly vulnerable to adversarial attacks but is not important for the task of classification. We establish the theoretical setup for formalising the process of segregation, isolation and neutralization and substantiate it through empirical analysis on standard benchmarking datasets. The findings strongly indicate that mapping features into the input space preserves the significant patterns typically observed in the feature-space while adding major interpretability and therefore simplifies potential defensive mechanisms. © 2024 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep Models for Real-Time 4K Image Super-Resolution. NTIRE 2023 Benchmark and Report

Efficient Deep Models for Real-Time 4K Image Super-Resolutio...

引用

ieee computer society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Marcos V. Conde Eduard Zamfir Radu Timofte Daniel Motilla Cen Liu Zexin Zhang Yunbo Peng Yue Lin Jiaming Guo Xueyi Zou Yuyi Chen Yi Liu Jia Hao Youliang Yan Yuanfan Zhang Gen Li Lei Sun Lingshun Kong Haoran Bai Jinshan Pan Jiangxin Dong Jinhui Tang Mustafa Ayazoglu Bahri Batuhan Bilecen Mingxi Li Yuhang Zhang Xianjun Fan Yankai Sheng Long Sun Zibin Liu Weiran Gou Shaoqing Li Ziyao Yi Yan Xiang Dehui Kong Ke Xu Ganzorig Gankhuyag Kihwan Yoon Jin Zhang Gaocheng Yu Feng Zhang Hongbin Wang Zhou Zhou Jiahao Chao Hongfan Gao Jiali Gong Zhengfeng Yang Zhenbing Zeng Chengpeng Chen Zichao Guo Anjin Park Yuqing Liu Qi Jia Hongyuan Yu Xuanwu Yin Kunlong Zuo Dongyang Zhang Ting Fu Zhengxue Cheng Shiai Zhu Dajiang Zhou Weichen Yu Lin Ge Jiahua Dong Yajun Zou Zhuoyuan Wu Binnan Han Xiaolin Zhang Heng Zhang Ben Shao Shaolong Zheng Daheng Yin Baijun Chen Mengyang Liu Marian-Sergiu Nistor Yi-Chung Chen Zhi-Kai Huang Yuan-Chun Chiang Wei-Ting Chen Hao-Hsiang Yang Hua-En Chang I-Hsiang Chen Chia-Hsuan Hsieh Sy-Yen Kuo Tu Vo Qingsen Yan Yun Zhu Jinqiu Su Yanning Zhang Cheng Zhang Jiaying Luo Youngsun Cho Nakyung Lee Computer Vision Lab University of Wurzburg Germany SIE FTG USA

This paper introduces a novel benchmark for efficient up-scaling as part of the NTIRE 2023 Real-Time Image Super-Resolution (RTSR) Challenge, which aimed to upscale images from 720p and 1080p resolution to native 4K (×2 and ×3 factors) in real-time on commercial GPUs. For this, we use a new test set containing diverse 4K images ranging from digital art to gaming and photography. We assessed the methods devised for 4K SR by measuring their runtime, parameters, and FLOPs, while ensuring a minimum PSNR fidelity over Bicubic interpolation. Out of the 170 participants, 25 teams contributed to this report, making it the most comprehensive benchmark to date and showcasing the latest advancements in real-time SR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Approach to classify different Beverages using Back Propagation Algorithm 3

Novel Approach to classify different Beverages using Back Pr...

引用

3rd ieee International conference on Computing, Communication, and Intelligent Systems, ICCCIS 2022

作者： Srivastava, Shikha Srivastava, Roopam Mgpg College Electronics Department UP Gorakhpur India Mgpg College Computer Application Department UP Gorakhpur India

ISBN: (纸本)9781665462006

This Complex problem like pattern recognition, computer vision, speech and picture identification, and others are solved using neural networks. An intelligent gas sensor (IGS) application neural network classifier is presented in this article. Utilizing reported data of a thick film tin oxide sensor array, its superior classification and learning ability is shown using an original and modified Back Propagation Algorithm for discriminating alcoholic beverages. Its ability to differentiate between various types of alcohol and alcoholic beverages demonstrates its greater classification and learning property. The novel model proposed in this study offers higher categorization accuracy. © 2022 ieee.

关键词： Torsional stress

来源：评论

学校读者我要写书评

暂无评论

Enriching ImageNet with Human Similarity Judgments and Psychological Embeddings

Enriching ImageNet with Human Similarity Judgments and Psych...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Roads, Brett D. Love, Bradley C. UCL Dept Expt Psychol London England

ISBN: (纸本)9781665445092

Advances in supervised learning approaches to object recognition flourished in part because of the availability of high-quality datasets and associated benchmarks. However, these benchmarks-such as ILSVRC-are relatively task-specific, focusing predominately on predicting class labels. We introduce a publicly-available dataset that embodies the task-general capabilities of human perception and reasoning. The Human Similarity Judgments extension to ImageNet (ImageNet-HSJ) is composed of a large set of human similarity judgments that supplements the existing ILSVRC validation set. The new dataset supports a range of task and performance metrics, including evaluation of unsupervised algorithms. We demonstrate two methods of assessment: using the similarity judgments directly and using a psychological embedding trained on the similarity judgments. This embedding space contains an order of magnitude more points (i.e., images) than previous efforts based on human judgments. We were able to scale to the MI 50,000 image ILSVRC validation set through a selective sampling process that used variational Bayesian inference and model ensembles to sample aspects of the embedding space that were most uncertain. To demonstrate the utility of ImageNet-HSJ, we used the similarity ratings and the embedding space to evaluate how well several popular models conform to human similarity judgments. One finding is that the more complex models that perform better on task-specific benchmarks do not better conform to human semantic judgments. In addition to the human similarity judgments, pre-trained psychological embeddings and code for inferring variational embeddings are made publicly available. ImageNet-HSJ supports the appraisal of internal representations and the development of more humanlike models.

关键词： Measurement computer vision Supervised learning Semantics Psychology Focusing Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Offset-Based Marker Placement for BIM Alignment in Mixed Reality

Offset-Based Marker Placement for BIM Alignment in Mixed Rea...

引用

2023 ieee International conference on Image Processing Challenges and workshops, ICIPCW 2023

作者： Einizinab, Sajjad Khoshelham, Kourosh Winter, Stephan Christopher, Philip Building 4.0 CRC1 Victoria3145 Australia University of Melbourne Department of Infrastructure Engineering ParkvilleVIC3010 Australia

ISBN: (纸本)9798350302585

Mixed reality (MR) visualization, which involves displaying virtual content mixed with a view of the real-world, has recently been explored for the inspection of building work. This process requires aligning a building information model (BIM) with physical construction sites. However, achieving accurate alignment poses challenges in MR applications. Marker-based methods, although more reliable, have limitations in complex environments where pre-installed markers are inaccessible in certain locations and their installation and maintenance are costly and labor-intensive. This paper introduces a new offset-based marker placement method to align BIM models in MR. This approach involves placing markers offset from the corners determined by the geometric features of the building. The markers are placed during the registration process, without the need for a pre-installation stage. The effectiveness of the method is demonstrated on a site with pipes of different sizes, showing that the offset-based markers provide accurate BIM alignment, comparable to conventional marker-based methods. © 2023 ieee.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2021 Challenge on Video Super-Resolution

NTIRE 2021 Challenge on Video Super-Resolution

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Son, Sanghyun Lee, Suyoung Nah, Seungjun Timofte, Radu Lee, Kyoung Mu Chan, Kelvin C. K. Zhou, Shangchen Xu, Xiangyu Loy, Chen Change Jiang, Boyuan Lin, Chuming Dong, Yuchun Luo, Donghao Chu, Wenqing Ji, Xiaozhong Yang, Siqian Tai, Ying Wang, Chengjie Li, Jilin Huang, Feiyue Chen, Chengpeng Chu, Xiaojie Zhang, Jie Lu, Xin Chen, Liangyu Lin, Jing Du, Guodong Hao, Jia Zou, Xueyi Zhang, Qi Jiang, Lielin Li, Xin Zheng, He Liu, Fanglong He, Dongliang Li, Fu Dang, Qingqing Yi, Peng Wang, Zhongyuan Jiang, Kui Jiang, Junjun Ma, Jiayi Chen, Yuxiang Wang, Yutong Liu, Ting Sun, Qichao Liang, Huanwei Li, Yiming Li, Zekun Ruan, Zhubo Shang, Fanjie Guo, Chen Li, Haining Luo, Renjun Shen, Longjie Zafirouli, Kassiani Karageorgos, Konstantinos Konstantoudakis, Konstantinos Dimou, Anastasios Daras, Petros Song, Xiaowei Zhuo, Xu Liu, Hanxi Guo, Mengxi Li, Junlin Li, Yu Zhu, Ye Wang, Qing Zhao, Shijie Sun, Xiaopeng Zhan, Gen Xie, Tangxin Jia, Yu Lu, Yunhua Zhang, Wenhao Sun, Mengdi Michelini, Pablo Navarrete Zhang, Xueheng Jiang, Hao Chen, Zhiyu Chen, Li Xiong, Zhiwei Xiao, Zeyu Xu, Ruikang Cheng, Zhen Fu, Xueyang Song, Fenglong Luo, Zhipeng Yao, Yuehan Dutta, Saikat Shah, Nisarg A. Das, Sourya Dipta Zhao, Peng Shi, Yukai Liu, Hongying Shang, Fanhua Liu, Yuanyuan Chen, Fei Yu, Fangxu Gao, Ruisheng Bai, Yixin Heo, Jeonghwan Yue, Shijie Li, Chenghua Li, Jinjing Zheng, Qian Gang, Ruipeng Song, Ruixia Wee, Seungwoo Jeong, Jechang Li, Chen Wen, Geyingjie Chai, Xinning Song, Li SNU ASRI Dept ECE Seoul South Korea Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland Nanyang Technol Univ S Lab Singapore Singapore Tencent YouTu Lab Shenzhen Peoples R China East China Normal Univ Shanghai Peoples R China Megvii Beijing Peoples R China Fudan Univ Shanghai Peoples R China Huawei Noahs Ark Lab Shanghai Peoples R China HiSilicon Shanghai Technol Co Ltd Shanghai Peoples R China Baidu Inc Dept Comp Vis Technol Vis Beijing Peoples R China Wuhan Univ Natl Engn Res Ctr Multimedia Software Wuhan Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin Peoples R China Wuhan Univ Elect Informat Sch Wuhan Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Peoples R China Meitu Inc MTlab Xiamen Peoples R China Xidian Univ Xian Peoples R China ITI CERTH Visual Comp Lab VCL Patras Greece Southeast Univ Nanjing Peoples R China Tencent PCG Appl Res Ctr ARC Shenzhen Peoples R China South China Univ Technol Guangzhou Peoples R China ByteDance Beijing Peoples R China Sun Yat Sen Univ Guangzhou Peoples R China China Elect Technol Cyber Secur Co Ltd Beijing Peoples R China BOE Technol Grp Co Ltd AIoT R&D Ctr Beijing Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China Univ Sci & Technol China Chengdu Peoples R China Huawei Noahs Ark Lab Beijing Peoples R China DeepBlue Technol Shanghai Co Ltd Shanghai Peoples R China Indian Inst Technol Madras Madras Tamil Nadu India Indian Inst Technol Jodhpur Jodhpur Rajasthan India Jadavpur Univ Kolkata India Hanyang Univ Seoul South Korea NCUT Beijing Peoples R China CASIA Beijing Peoples R China CUC Beijing Peoples R China NRTA Beijing Peoples R China

ISBN: (纸本)9781665448994

Super-Resolution (SR) is a fundamental computer vision task that aims to obtain a high-resolution clean image from the given low-resolution counterpart. This paper reviews the NTIRE 2021 Challenge on Video Super-Resolution. We present evaluation results from two competition tracks as well as the proposed solutions. Track 1 aims to develop conventional video SR methods focusing on the restoration quality. Track 2 assumes a more challenging environment with lower frame rates, casting spatio-temporal SR problem. In each competition, 247 and 223 participants have registered, respectively. During the final testing phase, 14 teams competed in each track to achieve state-of-the-art performance on video SR tasks.

关键词： computer vision Casting conferences Superresolution Focusing pattern recognition Image restoration

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery

Performance Evaluation of Segment Anything Model with Variat...

引用

ieee computer society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Yona Falinie A. Gaus Neelanjan Bhowmik Brian K. S. Isaac-Medina Toby P. Breckon Department of Computer Science Durham University UK Department of Engineering Durham University UK

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

The Segment Anything Model (SAM) is a deep neural network foundational model designed to perform instance segmentation which has gained significant popularity given its zero-shot segmentation ability. SAM operates by generating masks based on various input prompts such as text, bounding boxes, points, or masks, introducing a novel methodology to overcome the constraints posed by dataset-specific scarcity. While SAM is trained on an extensive dataset, comprising more than 11M images, it mostly consists of natural photographic (visible band) images with only very limited images from other modalities. Whilst the rapid progress in visual infrared surveillance and X-ray security screening imaging technologies, driven forward by advances in deep learning, has significantly enhanced the ability to detect, classify and segment objects with high accuracy, it is not evident if the SAM zero-shot capabilities can be transferred to such modalities beyond the visible spectrum. For this reason, this work comprehensively assesses SAM capabilities in segmenting objects of interest in the X-ray and infrared imaging modalities. Our approach reuses and preserves the pre-trained SAM with three different prompts, namely bounding box, centroid and random points. We present several quantitative and qualitative results to showcase the performance of SAM on selected datasets. Our results show that SAM can segment objects in the X-ray modality when given a box prompt, but its performance varies for point prompts. Specifically, SAM performs poorly in segmenting slender objects and organic materials, such as plastic bottles. Additionally, we find that infrared objects are also challenging to segment with point prompts given the low-contrast nature of this modality. Overall, this study shows that while SAM demonstrates outstanding zero-shot capabilities with box prompts, its performance ranges from moderate to poor for point prompts, indicating that special consideration on the cross-modal gener

关键词： Image segmentation Visualization Infrared surveillance Accuracy Annotations Organic materials Streaming media

来源：评论

学校读者我要写书评

暂无评论

Enhancing Traffic Signal State Retrieval Reliability in Autonomous Buses Using a Dual-Camera System

Enhancing Traffic Signal State Retrieval Reliability in Auto...

引用

On-Line conference (ONCON), Industrial Electronics society Annual

作者： Ludburgh Miyajima Zhaocheng Gu Daishi Watabe Saitama Institute of Technology Fukaya Japan

ISBN: (数字)9798331540319

ISBN: (纸本)9798331540326

In the context of urban intelligent transportation systems (ITS), ensuring that autonomous buses can follow traffic flow to safeguard passenger safety is fundamental. To achieve this, these buses must accurately obtain the current status of traffic control systems, such as traffic signals. The advanced methods of traffic signal recognition typically rely on computer vision and pattern recognition algorithms, which allow the autonomous vehicle to gather information similarly to a human driver without requiring modifications to existing infrastructure. However, these algorithms face challenges like high computational demands, failure to recognize objects outside the camera's field of view, glare, low light, noise, or poor image quality. This study aims to explore methods for improving traffic signal information retrieval by enhancing existing computer vision-based recognition or through the integration of radio-based data acquisition. A proposed solution combines dual-camera systems with radio-based data collection, offering a more reliable and efficient traffic signal recognition system. This approach effectively enhances the safety of urban ITSs by leveraging a fusion of computer vision and radio technology.

关键词： YOLO Wireless communication computer vision Wireless sensor networks Face recognition Urban areas Traffic control Safety Autonomous vehicles Vehicles

来源：评论

学校读者我要写书评

暂无评论

ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

ClassSR: A General Framework to Accelerate Super-Resolution ...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Kong, Xiangtao Zhao, Hengyuan Qiao, Yu Dong, Chao Chinese Acad Sci Shenzhen Inst Adv Technol Key Lab Human Machine Intelligence Synergy Syst Shenzhen Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Shanghai AI Lab Shanghai Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc SIAT Branch Shenzhen Peoples R China

ISBN: (纸本)9781665445092

We aim at accelerating super-resolution (SR) networks on large images (2K-8K). The large images are usually decomposed into small sub-images in practical usages. Based on this processing, we found that different image regions have different restoration difficulties and can be processed by networks with different capacities. Intuitively, smooth areas are easier to super-solve than complex textures. To utilize this property, we can adopt appropriate SR networks to process different sub-images after the decomposition. On this basis, we propose a new solution pipeline - ClassSR that combines classification and SR in a unified framework. In particular, it first uses a Class-Module to classify the sub-images into different classes according to restoration difficulties, then applies an SR-Module to perform SR for different classes. The Class-Module is a conventional classification network, while the SR-Module is a network container that consists of the to-be-accelerated SR network and its simplified versions. We further introduce a new classification method with two losses - Class-Loss and Average-Loss to produce the classification results. After joint training, a majority of sub-images will pass through smaller networks, thus the computational cost can be significantly reduced. Experiments show that our ClassSR can help most existing methods (e.g., FSRCNN, CARN, SRResNet, RCAN) save up to 50% FLOPs on DIV8K datasets. This general framework can also be applied in other low-level vision tasks.

关键词： Training computer vision Superresolution Pipelines Containers Image restoration pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Modernized Training of U-Net for Aerial Semantic Segmentation

Modernized Training of U-Net for Aerial Semantic Segmentatio...

引用

ieee Winter Applications and computer vision workshops (WACVW)

作者： Jakub Straka Ivan Gruber Department of Cybernetics Plzeň Czech Republic Department of Cybernetics and New Technologies for the Information Society Plzeň Czech Republic

In this paper, we propose an improved training protocol of U-Net architecture for the semantic segmentation of aerial images. We test our approach on the challenging FLAIR #2 dataset. We present an extensive ablation study on the influence of different approach components on the overall performance. The ablation study includes a comparison of different model backbones, image augmentations, learning rate schedulers, loss functions, and training procedures. We additionally propose a two-stage training procedure and evaluate different options for the model ensemble. Based on the results we design the final setup of the model training protocol. This final setup decreases the relative error by approximately 18% and achieves mIoU equal to 0.641, which is a new state-of-the-art result. Our code is available at: h ttps://***/strakaj/U-Net-for-remote-sensing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 171 172 173 174 175 176 177 178 179 180 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：