• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Acoustics, Speech and Signal Processing >DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
【24h】

DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification

机译：DADA：极低数据体制分类的深度对抗数据增强

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing - including unlabeled data - else. Such regimes arise from practical situations where not only data labeling but also data collection itself is expensive. We propose a deep adversarial data augmentation (DADA) technique to address the problem, in which we elaborately formulate data augmentation as a problem of training a class-conditional and supervised generative adversarial network (GAN). Specifically, a new discriminator loss is proposed to fit the goal of data augmentation, through which both real and augmented samples are enforced to contribute to and be consistent in finding the decision boundaries. Tailored training techniques are developed accordingly. Source code is available at https://github.com/SchafferZhang/DADA.
机译：深度学习彻底改变了分类的性能，但同时需要足够的标记数据来进行训练。在数据不足的情况下，尽管已开发出许多技术来解决过度拟合问题，但如果人们尝试训练深度网络，尤其是在病态的极低数据体制下，挑战仍然存在：只有一小部分带标签的数据可用，而没有-包括未标记的数据-其他。这种机制是由于实际情况而产生的，在这些情况下，不仅数据标记而且数据收集本身也很昂贵。我们提出了一种深度对抗数据增强（DADA）技术来解决该问题，其中，我们精心地将数据增强公式化为训练类条件和监督的生成对抗网络（GAN）的问题。具体而言，提出了一种新的鉴别器损失，以适应数据扩充的目标，通过该损失，实际样本和扩充样本都将被强制执行，从而有助于并一致地找到决策边界。相应地开发了量身定制的培训技术。源代码可从https://github.com/SchafferZhang/DADA获得。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号