首页> 外文期刊>IEEE Transactions on Image Processing >Piecewise Classifier Mappings: Learning Fine-Grained Learners for Novel Categories With Few Examples
【24h】

Piecewise Classifier Mappings: Learning Fine-Grained Learners for Novel Categories With Few Examples

机译:分段分类器映射:通过很少的示例为新类别学习细粒度的学习者

获取原文
获取原文并翻译 | 示例
           

摘要

Humans are capable of learning a new fine-grained concept with very little supervision, e.g., few exemplary images for a species of bird, yet our best deep learning systems need hundreds or thousands of labeled examples. In this paper, we try to reduce th
机译:人类能够在很少的监督下学习新的细粒度概念,例如,很少有鸟类的示例性图像,但是我们最好的深度学习系统需要成百上千个带有标签的示例。在本文中,我们尝试减少

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