论文阅读:Multi-Scale Triplet CNN for Person Re-Identification
2017-03-02 10:55
1221 查看
中国科技大学的Jiawei Liu等发表在Acm on Multimedia Conference上的论文。作者提出一个多尺度的triplet CNN,在一个数据集Market1501上表现出好的性能。
网络结构如下:
![](https://oscdn.geek-share.com/Uploads/Images/Content/202011/07/7a1cc5dce5b116593aee8e11e20e66f1)
Triplet loss
![](https://oscdn.geek-share.com/Uploads/Images/Content/202011/07/4699a640bd5a5c0f657bab2d57589fdb)
主要改进:同时训练了三个不同尺度的网络,对于低尺度用了shallow network(2个卷积+池化),不变尺度的用了5个卷积(池化)。最后进行特征的组合。
网络结构如下:
Triplet loss
主要改进:同时训练了三个不同尺度的网络,对于低尺度用了shallow network(2个卷积+池化),不变尺度的用了5个卷积(池化)。最后进行特征的组合。
相关文章推荐
- 1703.In Defense of the Triplet Loss for Person Re-Identification 论文阅读笔记
- 【论文笔记】In Defense of the Triplet Loss for Person Re-Identification
- 论文阅读:Joint Learning of Single-image and Cross-image Representations for Person Re-identification
- [论文翻译]Pedestrian Alignment Network for Large-scale Person Re-Identification
- part-aligned系列论文:1707.ICCV.Pedestrian Alignment Network for Large-scale Person Re-identification 论文
- 论文阅读《Joint Learning of Single-image Cross-image Representations for Person Re-identification》
- 论文阅读:An Enhanced Deep Feature Representation for Person Re-identification
- Query-Adaptive Late Fusion for Image Search and Person Re-identification阅读笔记
- 1606.End--to-End Comparative Attention Networks for Person Re-identification 论文笔记
- 【论文笔记】Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
- 1701.Re-ranking Person Re-identification with k-reciprocal Encoding--PRW 论文阅读笔记
- 论文笔记之: Person Re-Identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function
- 【Person Re-ID】In Defense of the Triplet Loss for Person Re-Identification
- Paper Reading: In Defense of the Triplet Loss for Person Re-Identification
- 论文笔记:Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
- 1604.Joint Detection and Identification Feature Learning for Person Search论文阅读笔记
- part-aligned系列论文:1707.Deeply-Learned Part-Aligned Representations for Person Re-Identification 论文笔记
- 【论文笔记】Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
- 行人检索--Beyond triplet loss: a deep quadruplet network for person re-identification
- 【Person Re-id】A Discriminatively Learned CNN Embedding for Person Re-identification