• 问答
  • 技术
  • 实践
  • 资源
【框架】PyTorch 图像检索框架
技术讨论

作者:leeesangwon
GitHub项目:PyTorch-Image-Retrieval


本文介绍了一个PyTorch 图像检索框架,可以很好的实现N-pair Loss (NIPS 2016) Angular Loss (CVPR 2017)的图像检索任务


Loss functions

We implemented loss functions to train the network for image retrieval.
Batch sampler for the loss function borrowed from here.

  • N-pair Loss (NIPS 2016): Sohn, Kihyuk. "Improved Deep Metric Learning with Multi-class N-pair Loss Objective," Advances in Neural Information
    Processing Systems. 2016.
  • Angular Loss (CVPR 2017): Wang, Jian. "Deep Metric Learning with Angular Loss," CVPR, 2017

Self-attention module

We attached the self-attention module of the Self-Attention GAN to conventional classification networks (e.g. DenseNet, ResNet, or SENet).
Implementation of the module borrowed from here.

Data augmentation

We adopted data augmentation techniques used in Single Shot MultiBox Detector.

Post processing

We utilized the following post-processing techniques in the inference phase.


更多Awsome Github资源请关注:【Awsome】GitHub 资源汇总


推荐阅读:
【电子书】李沐大神《动手学深度学习》
ICCV 2019 野生东北虎再识别挑战赛双赛道冠军方案(含开源代码)
1987 ~2017 年历届 ICCV 最佳论文(Marr Prize Paper)汇总

file
△ 扫一扫关注 极市平台
每天推送最新CV干货

  • 0
  • 2
  • 5224
收藏
暂无评论
Find me
大咖

一个大的公司

  • 18,019

    关注
  • 266

    获赞
  • 54

    精选文章
近期动态
  • 哈工大深圳研究生院CV汪,请原谅我这一生放纵不羁爱CV~
文章专栏
  • Awsome-Github 资源列表