【数据增强】综述:A survey on Image Data Augmentation for Deep Learning

 主体部分来自论文《A survey on Image Data Augmentation for Deep Learning》,新增了一些近年的论文。

我认为问题的根本在于模型学习了数据中的bias。一个过拟合的模型会去学习数据中存在的bias,如人脸识别中的position bias,或是普遍存在的lighting bias等。在风格迁移中,会称为不同的domain,如白天/夜晚,雨天/晴天等。解决问题有两个思路:

1. 模型本身。控制模型的复杂度,使得模型去学习general而不是special的特征。比如通过dropout,使得模型不要太依赖一些局部特征,通过batch normalization,得到稳定的分布,避免复杂的函数去拟合。

2. 数据,打破数据中的偏见。比如风格迁移添加黑夜黄昏的图片等。

但在对抗攻击中我们会发现,图片小的改变就可能导致结果的巨变,这说明我们很难通过穷举所有的domain去让模型专注目标本身。因此我觉得Mixup类思路很巧妙,通过线性按比例相加生成新的图片和标签,让数据去“线性化”模型,使得模型尽可能简单。

我们的根本目标是让模型专注于目标的特征,而不是背景:避免模型复杂化(Mixup和cutout类算法,可以把避免模型过拟合的方法迁移过来)和减少数据bias。

整理了大部分数据增强方法的实现,和Learning data augmentation strategies for object detection、GridMask和Augmentation for small object detection三篇论文的方法,欢迎指出问题和star.

GitHub - zzl421/Data_Augmentation_Zoo_for_Object_Detection: Includes: Learning data augmentation strategies for object detection | GridMask data augmentation | Augmentation for small object detection in Numpy. Use RetinaNet with ResNet-18 to test these methods on VOC and KITTI.

  • 4
    点赞
  • 24
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Autoencoder-based data augmentation can have a significant influence on deep learning-based wireless communication systems. By generating additional training data through data augmentation, the performance of deep learning models can be greatly improved. This is particularly important in wireless communication systems, where the availability of large amounts of labeled data is often limited. Autoencoder-based data augmentation techniques can be used to generate synthetic data that is similar to the real-world data. This can help to address the problem of overfitting, where the deep learning model becomes too specialized to the training data and performs poorly on new, unseen data. By increasing the diversity of the training data, the deep learning model is better able to generalize to new data and improve its performance. Furthermore, autoencoder-based data augmentation can also be used to improve the robustness of deep learning models to channel variations and noise. By generating synthetic data that simulates different channel conditions and noise levels, the deep learning model can be trained to be more resilient to these factors. This can result in improved performance in real-world wireless communication scenarios, where channel conditions and noise levels can vary widely. In conclusion, autoencoder-based data augmentation can have a significant influence on deep learning-based wireless communication systems by improving the performance and robustness of deep learning models.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值