论文题目：Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identiﬁcation
还是香港中文大学的牛牛们写的paper.

有源码：https://github.com/Cysu/person_reid

Motivation

这篇paper主要是为了解决一些issues（例如person re-identification），这些应用没有large-scale datasets，但是有许多small datasets，从而采用多域学习。因此，本文提出用CNNs提取深度特征的pipeline。将所有的小数据集的训练数据组织在一起，组成一个large scale classification issue。这样训练出来的神经元有些对公共数据集有效，有的对单个数据集有效，于是，作者提出了Domain guided dropout（包括determinative 和 stochatistic ）,有效的提高了特征的性能。实验在七个数据上进行，包括（摘自作者发布的信息）：
1. CUHK03
2. CUHK01
3. PRID
4. VIPeR (I cannot find the link to the original dataset. This is my previous backup version.)
5. 3DPeS
6. i-LIDS (I cannot find the link to the original dataset. This is my previous backup version.)
7. Shinpuhkan (need to send an email to the authors)
所有数据集都分成train,val,和test，取所有的train sets 合并成一个大数据集进行训练，但微调只在前6个上进行，因为，最后一个数据集只有24个ID.

内容

参看：http://blog.csdn.net/lv26230418/article/details/51317180
这篇写的很详细

[CVPR2016]Learning Deep Feature Representations with Domain Guided Dropout for Person Re-id相关推荐

遥感图像-Deep Feature Alignment Neural Networks for Domain Adaptation of Hyperspectral Data高光谱数据深度特征对齐神经
Deep Feature Alignment Neural Networks for Domain Adaptation of Hyperspectral Data高光谱数据领域自适应的深度特征对齐神 ...
Domain Agnostic Learning with Disentangled Representations
Domain Agnostic Learning with Disentangled Representations 第一章领域未知的表示学习文章目录 Domain Agnostic Learni ...
ZH奶酪：【阅读笔记】Deep Learning, NLP, and Representations
中文译文:深度学习.自然语言处理和表征方法 http://blog.jobbole.com/77709/ 英文原文:Deep Learning, NLP, and Representations ht ...
Learning Policies for Adaptive Tracking with Deep Feature Cascades
Learning Policies for Adaptive Tracking with Deep Feature Cascades ICCV17 shotlight 作者:Chen Huang, C ...
Learning Policies for Adaptive Tracking with Deep Feature Cascades（深度增强学习、目标跟踪）
1.论文相关论文题目: "Learning Policies for Adaptive Tracking with Deep Feature Cascades." ICCV (2 ...
【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 ...
遥感-Deep Covariance Alignment for Domain Adaptive Remote Sensing Image Segmentation域自适应遥感图像分割中深度协方差对齐
Deep Covariance Alignment for Domain Adaptive Remote Sensing Image Segmentation域自适应遥感图像分割中的深度协方差对齐 0 ...
DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation 用于无监督异常分割的深度特征重建
DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation DFR:用于无监督异常分割的深度特征重建类型:公开 ...
指代消解_论文理解《Improving Coreference Resolution by Learning Entity-Level Distributed Representations》
论文<Improving Coreference Resolution by Learning Entity-Level Distributed Representations> 段落: ...

[CVPR2016]Learning Deep Feature Representations with Domain Guided Dropout for Person Re-id

Motivation

内容

[CVPR2016]Learning Deep Feature Representations with Domain Guided Dropout for Person Re-id相关推荐

最新文章

热门文章