RepNet-VehicleReID-master
所属分类：模式识别(视觉/语音等)
开发工具：Python
文件大小：463KB
下载次数：2
上传日期：2020-07-19 11:32:58
上 传 者：
sbchen
说明： #RepNet车辆重识别
##车辆ReID任务：
##车辆ReID任务的基本原则：</br>
利用双分支深卷积网络将原始车辆图像投影到欧几里德空间中，在该空间中可以直接用距离来度量任意两个车辆的相似性。</r>
为了简单起见，本文将三重态损失或耦合簇损失替换为广泛应用于人脸识别的弧损耗。
(# RepNet-Vehicle-ReID
Vehicle re-identification implementing RepNet
## Basic principle for vehicle ReID task: </br>
Using a two-branch deep convolutional network to project raw vehicle images into an Euclidean space where distance can be directly used to measure the similarity of arbitrary two vehicles. </r>
For simplicity, triplet loss or coupled cluster loss is replaced here by arc loss which is widely used in face recognition.)
文件列表:
ProcessVehicleID.py (11801, 2019-02-23)
RepNet.png (73518, 2019-02-23)
RepNet.py (55959, 2019-02-23)
RepNet2.png (132000, 2019-02-23)
TestResult.png (88691, 2019-02-23)
VehicleReIDTask.png (173696, 2019-02-23)
# RepNet-Vehicle-ReID
Vehicle re-identification implementing RepNet
## Vehicle ReID task:
## Basic principle for vehicle ReID task:
Using a two-branch deep convolutional network to project raw vehicle images into an Euclidean space where distance can be directly used to measure the similarity of arbitrary two vehicles.
For simplicity, triplet loss or coupled cluster loss is replaced here by arc loss which is widely used in face recognition.
# Test result
## Network structure:
## Reference:
[Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Liu_Deep_Relative_Distance_CVPR_2016_paper.pdf)
[Learning a repression network for precise vehicle search](https://arxiv.org/pdf/1708.02386.pdf)
## Dataset:
[VehicleID dataset](https://pan.baidu.com/s/1JKOysKjrlgReuxZ2ONCmUQ)
近期下载者：
相关文件：
收藏者：