• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Joint Conference on Neural Networks >Utilizing Information from Task-Independent Aspects via GAN-Assisted Knowledge Transfer
【24h】

Utilizing Information from Task-Independent Aspects via GAN-Assisted Knowledge Transfer

机译：通过GAN辅助知识转移利用与任务无关的信息

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

摘要

Observed data often have multiple labels with respect to different aspects. For example, a picture can have one label specifying the contents in terms of the object category such as aeroplane, building, cat, etc. and in the meanwhile have another label describing the image style such as photo-realistic or artistic. The central idea of this work is that any annotation of the data contains precious knowledge and is not to be foregone: an analytic task focusing on one aspect of the data can benefit from the knowledge transferred from the other aspects. We propose a passive knowledge transfer scheme for deep neural network training based on the generative adversarial nets (GANs). The adversarial training scheme encourages the nets to encode data into representations that are both discriminative for the target aspect and invariant with respect to the irrelevant aspects. We show that the scheme mixes the conditional distributions of the encoded data on the irrelevant aspects, by the theory on the link between the GAN framework and the Wasserstein metric in distribution spaces. Moreover, we empirically verified the method by i) classifying images despite influence by geometric transform and ii) recognizing the movements (geometric transform) regardless the image contents.
机译：观察到的数据通常在不同方面具有多个标签。例如，图片可以具有一个标签，该标签根据飞机，建筑物，猫等物体类别指定内容，同时具有描述图像样式的标签，例如照片级或艺术级。这项工作的中心思想是，对数据的任何注释都包含宝贵的知识，而不是被遗弃：专注于数据一个方面的分析任务可以从其他方面转移过来的知识中受益。我们提出了一种基于生成对抗网络（GAN）的用于深度神经网络训练的被动知识转移方案。对抗训练方案鼓励网络将数据编码为既可区分目标方面又相对于无关方面不变的表示形式。我们通过在分布空间中GAN框架和Wasserstein度量之间的联系的理论，证明了该方案在不相关的方面混合了编码数据的条件分布。此外，我们通过以下方法从经验上验证了该方法：i）不受几何变换的影响而对图像进行分类; ii）识别运动（几何变换）而与图像内容无关。

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