reid-strong-baseline

一揽子技巧和深度人员重新识别的强大基准。「Bag of Tricks and A Strong Baseline for Deep Person Re-identification」

  • 所有者: michuanhaohao/reid-strong-baseline
  • 平台: Linux, Mac
  • 许可证: MIT License
  • 分类:
  • 主题:
  • 喜欢:
    0
      比较:

Github星跟踪图

技巧包和强大的 ReID 基准

一揽子技巧和深人重新识别的强大基准。 CVPRW2019, Oral。

深度人员重新识别的强大基准和批次归一化瓶颈。 IEEE多媒体交易(已接受)。

[期刊版本(TMM)] [PDF] [幻灯片] [海报]

新闻! 基于强大的基准,我们在2020年AICity挑战赛上获得了第三名。[[PDF]] [[代码]]

新闻! 我们的期刊版本已被IEEE Transactions on Multimedia接受。

我们非常感谢您为我们的项目做出的贡献,并希望该项目可以为您的研究或工作提供帮助。

这些代码在ReID-baseline(ReID 基线)上扩展,该基线由我们的第一作者 Xingyu Liao 开源。

python2.7 和 pytorch0.4 开发了另一个重新实现。 [[链接]]

一个带有简单重新实现的小型 repo。 [[链接]]

我们的基准还可以在 Vehicle ReID 任务上实现出色的性能! [[链接]]

有了 Ranked List loss(CVPR2019)[[链接]],我们的基准可以实现更好的性能。 [[链接]]

@InProceedings{Luo_2019_CVPR_Workshops,
author = {Luo, Hao and Gu, Youzhi and Liao, Xingyu and Lai, Shenqi and Jiang, Wei},
title = {Bag of Tricks and a Strong Baseline for Deep Person Re-Identification},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}
@ARTICLE{Luo_2019_Strong_TMM, 
author={H. {Luo} and W. {Jiang} and Y. {Gu} and F. {Liu} and X. {Liao} and S. {Lai} and J. {Gu}}, 
journal={IEEE Transactions on Multimedia}, 
title={A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification}, 
year={2019}, 
pages={1-1}, 
doi={10.1109/TMM.2019.2958756}, 
ISSN={1941-0077}, 
}

作者

我们支持

  • 简单的数据集准备
  • 端到端培训和评估
  • 高模块化管理
  • 加快推理速度 [link]
  • 支持多GPU训练 [link]

绝招

  • 热身学习率(Warm up learning rate)
  • 随机擦除增强(Random erasing augmentation)
  • 标签平滑(Label smoothing)
  • 最后一步(Last stride)
  • BNNeck
  • 中心损耗(Center loss)

待办事项清单

将来,我们将

  • []支持更多数据集
  • 【支持更多型号】
  • []探索更多技巧

其余内容请参考《自述文件》。


主要指标

概览
名称与所有者michuanhaohao/reid-strong-baseline
主编程语言Python
编程语言Shell (语言数: 2)
平台Linux, Mac
许可证MIT License
所有者活动
创建于2019-03-16 14:28:00
推送于2020-04-23 06:04:46
最后一次提交2020-04-23 14:04:45
发布数0
用户参与
星数2.3k
关注者数50
派生数578
提交数68
已启用问题?
问题数219
打开的问题数40
拉请求数8
打开的拉请求数0
关闭的拉请求数1
项目设置
已启用Wiki?
已存档?
是复刻?
已锁定?
是镜像?
是私有?

Bag of Tricks and A Strong ReID Baseline

Bag of Tricks and A Strong Baseline for Deep Person Re-identification. CVPRW2019, Oral.

A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification. IEEE Transactions on Multimedia (Accepted).

(https://ieeexplore.ieee.org/document/8930088)
(http://openaccess.thecvf.com/content_CVPRW_2019/papers/TRMTMCT/Luo_Bag_of_Tricks_and_a_Strong_Baseline_for_Deep_Person_CVPRW_2019_paper.pdf)
(https://drive.google.com/open?id=1h9SgdJenvfoNp9PTUxPiz5_K5HFCho-V)
(https://drive.google.com/open?id=1izZYAwylBsrldxSMqHCH432P6hnyh1vR)

News! Our journal version has been accepted by IEEE Transactions on Multimedia.

We are very grateful for your contribution to our project and hope that this project can help your research or work.

The codes are expanded on a ReID-baseline , which is open sourced by our co-first author Xingyu Liao.

Another re-implement is developed by python2.7 and pytorch0.4. (https://github.com/wangguanan/Pytorch-Person-REID-Baseline-Bag-of-Tricks)

A tiny repo with simple re-implement. (https://github.com/lulujianjie/person-reid-tiny-baseline)

Our baseline also achieves great performance on Vehicle ReID task! (https://github.com/DTennant/reid_baseline_with_syncbn)

With Ranked List loss(CVPR2019)(http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Ranked_List_Loss_for_Deep_Metric_Learning_CVPR_2019_paper.pdf), our baseline can achieve better performance. (https://github.com/Qidian213/Ranked_Person_ReID)

@InProceedings{Luo_2019_CVPR_Workshops,
author = {Luo, Hao and Gu, Youzhi and Liao, Xingyu and Lai, Shenqi and Jiang, Wei},
title = {Bag of Tricks and a Strong Baseline for Deep Person Re-Identification},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}

@ARTICLE{Luo_2019_Strong_TMM, 
author={H. {Luo} and W. {Jiang} and Y. {Gu} and F. {Liu} and X. {Liao} and S. {Lai} and J. {Gu}}, 
journal={IEEE Transactions on Multimedia}, 
title={A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification}, 
year={2019}, 
pages={1-1}, 
doi={10.1109/TMM.2019.2958756}, 
ISSN={1941-0077}, 
}

Authors

We support

Bag of tricks

  • Warm up learning rate
  • Random erasing augmentation
  • Label smoothing
  • Last stride
  • BNNeck
  • Center loss

TODO list

In the future, we will

  • [] support more datasets
  • [] support more models
  • [] explore more tricks

Pipeline

Results (rank1/mAP)