「CV」 数据增强资源汇总

1 综述

2 理论

3 GAN

4 AutoEncoder

1. Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder
   2019-05-22 paper

5 应用

5.1 分割

1. Defective samples simulation through Neural Style Transfer for automatic surface defect segment
   2019-10-08 paper
   GAN 生成缺陷样本；

6 其他

1. Some improvements on deep convolutional neural network based image classification
   2013-12-19 paper | torch | blog | openreview | paper with code | blog
   颜色抖动

2. Improved Regularization of Convolutional Neural Networks with Cutout
   2017-08-15 paper | pytorch-official

3. AutoAugment: Learning Augmentation Policies from Data
   CVPR 2019 2018-05-24 paper | tensorflow-official | numpy

4. When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation
   2019-06-07 paper

5. Autoaugment: Learning augmentation strategies from data
   CVPR 2019 2019 paper | blog
   $\bullet \bullet$
   探讨了监督学习中的数据增广问题；

6. Online Hyper-parameter Learning for Auto-Augmentation Strategy
   2019-05-17 paper
   $\bullet \bullet$
   在线超参数据增强；

7. Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
   2019-11-16 paper

---

TOP

附录

A 资源

1. 样本增广自动化-AutoAugment论文解读

B 参考资料

1. 几种新的regularization方法