[CVPR2016]Learning Deep Feature Representations with Domain Guided Dropout for Person Re-id
2016-11-05 11:22
603 查看
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
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.
这篇写的很详细
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
相关文章推荐
- [2016,CVPR] Learning Deep Feature Representations with Domain Guided Dropout for Person Re-id
- 论文笔记之---Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identificatio
- 论文研读--Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
- 1604. Learning deep feature representations with domain guided dropout for re-id论文阅读笔记
- 【Person Re-ID】Deep Representation Learning with Part Loss for Person Re-Identification
- Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-ide
- 【Person Re-ID】Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
- CVPR2015:An Improved Deep Learning Architecture for Person Re-Identificaton
- 【Person Re-ID】Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
- [Paper note] Joint Learning of Single-image and Cross-image Representations for Person Re-id.
- [2016,arXiv] An Enhanced Deep Feature Representation for Person Re-identification
- Deep Metric Learning for Person Re-Identification
- 【行人识别】Deep Transfer Learning for Person Re-identification
- Learning hierarchical representations for face verification with convolutional deep belief networks
- 行人检索“An Improved Deep Learning Architecture for Person Re-Identification”
- Deep Image Retrieval: Learning global representations for image search. In ECCV, 2016.
- 【文献阅读】ResNet-Deep Residual Learning for Image Recognition--CVPR--2016
- 论文阅读《Joint Learning of Single-image Cross-image Representations for Person Re-identification》
- 【行人识别】Deep Transfer Learning for Person Re-identification
- 【论文笔记】Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification