...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on multimedia >A Strong Baseline and Batch Normalization Neck for Deep Person Re-Identification
【24h】

A Strong Baseline and Batch Normalization Neck for Deep Person Re-Identification

机译：深层重新识别的强大基线和批量标准化颈部

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

This study proposes a simple but strong baseline for deep person re-identification (ReID). Deep person ReID has achieved great progress and high performance in recent years. However, many state-of-the-art methods design complex network structures and concatenate multi-branch features. In the literature, some effective training tricks briefly appear in several papers or source codes. The present study collects and evaluates these effective training tricks in person ReID. By combining these tricks, the model achieves 94.5% rank-1 and 85.9% mean average precision on Market1501 with only using the global features of ResNet50. The performance surpasses all existing global- and part-based baselines in person ReID. We propose a novel neck structure named as batch normalization neck (BNNeck). BNNeck adds a batch normalization layer after global pooling layer to separate metric and classification losses into two different feature spaces because we observe they are inconsistent in one embedding space. Extended experiments show that BNNeck can boost the baseline, and our baseline can improve the performance of existing state-of-the-art methods.
机译：本研究提出了一种简单但强烈的基线对深层重新识别（Reid）。近年来，深部队Reid取得了巨大的进步和高性能。然而，许多最先进的方法设计复杂的网络结构和连接多分支特征。在文献中，一些有效的培训技巧出现在几篇论文或源代码中。本研究收集并评估了人民REID的这些有效的培训技巧。通过组合这些技巧，该模型在Market1501上实现了94.5％的秩-1和85.9％的平均精度，只有使用Reset50的全局功能。该性能超越了人民Reid的所有现有全球和基于部分的基础。我们提出了一种名为批量标准化颈部（BNNEK）的新型颈部结构。 BNNeck在全局池层后添加批量归一化层，以将度量标准和分类损耗分成两个不同的特征空间，因为我们观察到它们在一个嵌入空间中不一致。扩展实验表明，BNNeck可以提高基线，我们的基线可以提高现有最先进方法的性能。

著录项

  • 来源
    《IEEE transactions on multimedia》 |2020年第10期|2597-2609|共13页
  • 作者

    Luo Hao; Jiang Wei; Gu Youzhi; Liu Fuxu; Liao Xingyu; Lai Shenqi; Gu Jianyang;

  • 作者单位

    Zhejiang Univ Coll Control Sci & Enginneering State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China;

    Zhejiang Univ Coll Control Sci & Enginneering State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China;

    Zhejiang Univ Coll Control Sci & Enginneering State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China;

    Ping An Technol Shenzhen 518000 Peoples R China;

    Chinese Acad Sci Beijing 100190 Peoples R China;

    Xi An Jiao Tong Univ Xian 710049 Peoples R China;

    Zhejiang Univ Coll Control Sci & Enginneering State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China;

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

    Person ReID; baseline; tricks; BNNeck; deep learning;

    机译：人雷德;基线;技巧;BNNECK;深度学习;

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