首页> 外文期刊>IEEE Transactions on Image Processing >Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation
【24h】

Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation

机译:通过选择性知识蒸馏在野外进行低分辨率人脸识别

获取原文
获取原文并翻译 | 示例

摘要

Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this problem, a feasible solution is compressing a complex face model to achieve higher speed and lower memory at the cost of minimal performance drop. Inspired by that, this paper proposes a learning approach to recognize low-resolution faces via selective knowledge distillation. In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively. The teacher stream is represented by a complex CNN for high-accuracy recognition, and the student stream is represented by a much simpler CNN for low-complexity recognition. To avoid significant performance drop at the student stream, we then selectively distil the most informative facial features from the teacher stream by solving a sparse graph optimization problem, which are then used to regularize the fine-tuning process of the student stream. In this way, the student stream is actually trained by simultaneously handling two tasks with limited computational resources: approximating the most informative facial cues via feature regression, and recovering the missing facial cues via low-resolution face classification. Experimental results show that the student stream performs impressively in recognizing low-resolution faces and costs only 0.15-MB memory and runs at 418 faces per second on CPU and 9433 faces per second on GPU.
机译:通常,野外使用面部识别模型需要以极低的计算成本来识别低分辨率面部。为了解决这个问题,一种可行的解决方案是以最小的性能下降为代价,压缩复杂的面部模型以实现更高的速度和更低的内存。受此启发,本文提出了一种通过选择性知识提炼识别低分辨率人脸的学习方法。在这种方法中,首先对两流卷积神经网络(CNN)进行初始化,以分别通过教师流和学生流识别高分辨率面孔和分辨率退化的面孔。教师流由用于高精度识别的复杂CNN表示,学生流由用于低复杂度识别的简单得多的CNN表示。为了避免在学生流中出现明显的性能下降,我们然后通过解决稀疏图优化问题,有选择地从教师流中分发最有用的面部特征,然后将其用于规范学生流的微调过程。通过这种方式,实际上通过同时处理两个任务且使用有限的计算资源来训练学生流:通过特征回归来近似提供最多信息的面部提示,以及通过低分辨率的面部分类来恢复丢失的面部提示。实验结果表明,学生流在识别低分辨率人脸方面表现出色,仅花费0.15 MB的内存,在CPU上每秒以418张面孔运行,在GPU上以每秒9433张面孔运行。

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