【框架】PyTorch 图像检索框架
source link: https://bbs.cvmart.net/articles/953
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
【框架】PyTorch 图像检索框架
1年前 ⋅ 2741 ⋅ 0 ⋅ 2
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) 和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.
- Moving the origin of the feature space to the center of the feature vectors
- L2-normalization
- Average query expansion
- Database-side feature augmentation
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
△ 扫一扫关注 极市平台
每天推送最新CV干货
微信公众号: 极市平台(ID: extrememart )
每天推送最新CV干货
版权声明:自由转载-非商用-非衍生-保持署名(创意共享3.0许可证)
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK