...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Image Processing >Multi-Task Deep Relative Attribute Learning for Visual Urban Perception
【24h】

Multi-Task Deep Relative Attribute Learning for Visual Urban Perception

机译：视觉城市认知的多任务深度相对属性学习

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Visual urban perception aims to quantify perceptual attributes (e.g., safe and depressing attributes) of physical urban environment from crowd-sourced street-view images and their pairwise comparisons. It has been receiving more and more attention in computer vision for various applications, such as perceptive attribute learning and urban scene understanding. Most existing methods adopt either 1) a regression model trained using image features and ranked scores converted from pairwise comparisons for perceptual attribute prediction or 2) a pairwise ranking algorithm to independently learn each perceptual attribute. However, the former fails to directly exploit pairwise comparisons while the latter ignores the relationship among different attributes. To address them, we propose a multi-task deep relative attribute learning network (MTDRALN) to learn all the relative attributes simultaneously via multi-task Siamese networks, where each Siamese network will predict one relative attribute. Combined with deep relative attribute learning, we utilize the structured sparsity to exploit the prior from natural attribute grouping, where all the attributes are divided into different groups based on semantic relatedness in advance. As a result, MTDRALN is capable of learning all the perceptual attributes simultaneously via multi-task learning. Besides the ranking sub-network, MTDRALN further introduces the classification sub-network, and these two types of losses from two sub-networks jointly constrain parameters of the deep network to make the network learn more discriminative visual features for relative attribute learning. In addition, our network can be trained in an end-to-end way to make deep feature learning and multi-task relative attribute learning reinforces each other. Extensive experiments on the large-scale Place Pulse 2.0 dataset validate the advantage of our proposed network. Our qualitative results along with visualization of saliency maps also show that the proposed network is able to learn effective features for perceptual attributes.
机译：视觉城市认知旨在量化来自人群街道视图图像及其成对比较的物理城市环境的感知属性（例如，安全和令人沮丧的属性）。它在各种应用中的计算机愿景中受到了越来越多的关注，例如被看法属性学习和城市场景理解。大多数现有方法采用1）使用图像特征培训的回归模型，并从对感知属性预测的成对比较转换为2）一个成对排名算法以独立地学习每个感知属性。然而，前者未能直接利用成对比较，而后者忽略了不同属性之间的关系。为了解决它们，我们提出了一个多任务深度相对属性学习网络（MTDRALN）来通过多任务暹罗网络同时学习所有相对属性，其中每个暹罗网络将预测一个相对属性。结合深度相对属性学习，我们利用结构化的稀疏性来利用自然属性分组的前一部分，其中所有属性都基于提前的语义相关性分为不同的组。结果，MTDRALN能够通过多任务学习同时学习所有感知属性。除了排名子网络之外，MTDRALN还介绍了分类子网络，以及来自两个子网的这两种类型的损耗共同约束深网络的参数，使网络了解相对属性学习的更多辨别性视觉特征。此外，我们的网络可以以端到端的方式培训，使深度特征学习和多任务相对属性学习彼此加强。大规模地点脉冲2.0数据集的广泛实验验证了我们所提出的网络的优势。我们的定性结果随着显着性图的可视化也表明，所提出的网络能够为感知属性学习有效的特征。

著录项

  • 来源
    《IEEE Transactions on Image Processing》 |2020年第2020期|657-669|共13页
  • 作者

    Min Weiqing; Mei Shuhuan; Liu Linhu; Wang Yi; Jiang Shuqiang;

  • 作者单位

    Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China|Univ Chinese Acad Sci Beijing 100049 Peoples R China;

    Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China|Shandong Univ Sci & Technol Coll Math & Syst Sci Qingdao 266590 Shandong Peoples R China;

    Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China|Univ Chinese Acad Sci Beijing 100049 Peoples R China;

    Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China;

    Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China|Univ Chinese Acad Sci Beijing 100049 Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Visualization; Task analysis; Deep learning; Urban areas; Correlation; Computer vision; Predictive models; Visual urban perception; relative attribute; multi-task learning;

    机译：可视化;任务分析;深入学习;城市地区;相关;计算机愿景;预测模型;视觉城市感知;相对属性;多任务学习;多任务学习;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号