CVPR2017: Learning Deep Context-aware Features over Body and Latent Parts for
论文查看
作者是中科院的Dangwei Li等。这篇工作是multi-class person identification tasks,主要创新有三点:(1)用空洞卷积(dilated conv)进行多尺度特征提取,减少传统CNN提取特征的信息损失;(2)利用Spatial Transformer Networks (STN,其中作者设置了三个参数限制) 提取可变的body-part,相比较于rigid divid, 能减少背景的影响; (3)将full body特征和parts特征融合,在identification classification 指导下,学习网络参数。
Yu, Fisher, and Vladlen Koltun. “Multi-scale context aggregation by dilated convolutions.” arXiv preprint arXiv:1511.07122 (2015).
Part 4 Experiments
4.1 Datasets and protocols
本节分成Datasets和protocols两部分。
Datasets: 第一段先整体介绍下哪些数据集上进行实验,其他段再分数据集单独介绍。
Protocols:介绍哪个数据集上进行哪些评估。
4.2 Implementation Details
分为Model , optimization 和 Data preprocessing 三部分
Model: 指出除了总的网络外,为了单独分析full body and body parts,抽出了两个sub models.
Optimization: 在caffe上实现,BP计算梯度,学习率等。
Data preprocessing :160x60, 1.0/256, image horizontally reflect
4.3 Comparison with state-of-the-art methods
分数据集进行比较,每个数据集一个单独的部分。
- For the CUHK03 dataset, we compare our method with many existing
approaches, including XX, XX….. - Compared with XXXX, such as XXX, the proposed XXXX improves the Rank-1 identification rate by 11.66% and 13.29% on the labeled and detected datasets respectively.
- Compared with XXXXX, our XXXX improves the Rank-1 identification rate by 2.93% and mAP by 4.22%.
4.4 Effectiveness of MSCAN(多尺度网络)
To determine the effectiveness of …., we explore four variants of … to learn IDE feature based on the whole body image.
选择一个数据集Market1501进行评估,分别设定dilated ratio 为1,2,3,4,指出3是个合适的选择(4的时候比3进展了一点点)
4.5 Effectiveness of Latent part location
(1)Learned parts vs. rigid parts:选择Market1501比较学习到部分和硬性指定的部分对结果的影响。
(2)可视化的方式展示学习到的部分和硬性分割的部分区别:学习到的部分由较大的重叠,同时包含较少的背景
(3)Effectiveness of location loss 评估约束的作用。
在基于部分的网络上评估约束(Market1501)
4.6 Cross-dataset Evaluation
在其他数据集上的模型迁移到VIPeR,分别验证了直接迁移和微调后的性能。
————————————————————————————————
关于dilated conv, 摘自知乎:
作者:谭旭
链接:https://www.zhihu.com/question/54149221/answer/192025860
来源:知乎
著作权归作者所有。
CVPR2017: Learning Deep Context-aware Features over Body and Latent Parts for相关推荐
- Learning Deep Features for Discriminative Localization -CAM方法帮助若监督学习研究实现物体定位论文阅读笔记
作者:18届会长cyl 时期: 2020-9-11 论文<Learning Deep Features for Discriminative Localization> 期刊:2016CV ...
- Learning Deep Learning(学习深度学习)
作者:chen_h 微信号 & QQ:862251340 微信公众号:coderpai 简书地址:https://www.jianshu.com/p/e98c5f61a6f2 Learning ...
- 【机器学习笔记】可解释机器学习-学习笔记 Interpretable Machine Learning (Deep Learning)
[机器学习笔记]可解释机器学习-学习笔记 Interpretable Machine Learning (Deep Learning) 目录 [机器学习笔记]可解释机器学习-学习笔记 Interpre ...
- 目标检测--Object Detection via Aspect Ratio and Context Aware
Object Detection via Aspect Ratio and Context Aware Region-based Convolutional Networks https://arxi ...
- [CVPR2016]Learning Deep Feature Representations with Domain Guided Dropout for Person Re-id
论文题目:Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification 还是 ...
- PaperNotes(9)-Learning deep energy model: contrastive divergence vs. Amortized MLE
Learning deep energy model: contrastive divergence vs. Amortized MLE abstract 1 Introduction 2 Backg ...
- 活体检测论文研读三:Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision 论文简介 一.指出先前的深度学习方法将人脸反欺 ...
- [人脸活体检测] 论文: Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision 论文简介 与人脸生理相关的rppG信号被研究者 ...
- Learning Deep Models for Face Anti-Spoofing_ Binary or Auxiliary Supervision
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision 标签(空格分隔): anti-spoofing ...
最新文章
- SQL Server孤立账户解决办法
- 12月第四周安全回顾:双节期间微软忙补新漏洞,新Hash将测试
- DevExpress ChartControl大数据加载时有哪些性能优化方法
- kafka是存储到本地磁盘么_【漫画】Kafka是如何实现高性能的?
- matlab中ismember_MATLAB 代码格式化简易版
- 计算机网络基础系列(八)TCP三次握手、四次挥手、可靠数据传输、拥塞控制和UDP
- SAPUI5教程——URLHelper的使用技巧
- mysql2008安装失败_SQL Server 2008 安装失败问题总结
- 数字积分法直线插补c语言,数字积分法的直线插补.ppt
- python微信推送{u‘errcode‘: 40008, u‘errmsg‘: u‘invalid message type rid: 6111061f-19703d5b
- golang连接FTP服务器并下载
- leet70:爬楼梯
- k8s(18)之污点与容忍
- 算术编码如何将原始数据编码为二进制
- 日语输入法时的部分实用快捷键
- CSAPP_Chapter1
- python scrapy 简单教程_python之scrapy入门教程
- 自动驾驶专业名词简写简写缩写
- 何制作手机自适应网页
- 在哪下载短视频?有哪些网站可以避免侵权?
热门文章
- 软考高项之沟通与干系人管理-背诵记忆
- 基于Java的RDMA高性能通信库(二):Java Socket Over RDMA
- 用泰勒公式算sin cos用c语言,用泰勒公式求sin(x)的近似值
- tomcat war java_java – 启动Tomcat WAR
- 2020.2idea怎么创建html模块_利用idea快速搭建一个项目
- win2003 https 网站的图文配置教程
- 重新更新了,账号都丢了,重新找回的
- Le Chapitre VI
- Java 读写Properties配置文件(转)
- 理解 Azure 虚拟机的性能监视