首页> 外国专利> METHOD AND SYSTEM FOR IMPROVING IMAGE COMPRESSION EFFICIENCY BASED ON DEEP LEARNING

METHOD AND SYSTEM FOR IMPROVING IMAGE COMPRESSION EFFICIENCY BASED ON DEEP LEARNING

机译:基于深度学习提高图像压缩效率的方法和系统

摘要

Disclosed is a method and system for improving image compression efficiency based on deep learning. The encoder of the deep learning network structure for image compression can be configured as an asymmetric network structure with a larger number of layers than the decoder of the deep learning network structure for image decompression. By applying (pruning), at least some connections of the deep learning network constituting the decoder can be removed.
机译:公开了一种基于深度学习改善图像压缩效率的方法和系统。图像压缩的深学习网络结构的编码器可以被配置为具有比图像解压缩的深度学习网络结构的解码器更多的层的非对称网络结构。通过应用(修剪),可以删除构成解码器的深度学习网络的至少一些连接。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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