用桥接蒸馏让轻量模型高效识别低分辨率人脸
Efficient Low-Resolution Face Recognition via Bridge Distillation
- 通过两阶段蒸馏，将高分辨模型知识迁移到低分辨人脸
- 模型仅0.21M参数，识别速度达每秒14705张（GPU）
- 适合移动端部署，兼顾速度与识别准确率
野外人脸识别正朝着轻量化模型、快速推理和分辨率自适应能力发展。本文提出一种桥接蒸馏方法，将基于私有高分辨率人脸预训练的复杂模型，转化为适用于低分辨率人脸识别的轻量模型。该方法通过两步蒸馏解决跨数据集分辨率适配的知识迁移问题：第一步进行跨数据集蒸馏，将私有高分辨率人脸先验知识迁移至公开高分辨率人脸，生成紧凑且具有判别性的特征；第二步进行分辨率自适应蒸馏，通过多任务学习将知识进一步迁移到合成低分辨率人脸。学生模型在学习低分辨率表示的同时模仿适配后的高分辨率知识，构建出高效且准确的轻量级模型。实验表明，该模型仅需0.21M参数和0.057MB内存，在GPU、CPU和移动设备上分别实现每秒14,705、~934和763张人脸的识别速度。
原文摘要 · Abstract (English)
Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability. In this paper, we propose a bridge distillation approach to turn a complex face model pretrained on private high-resolution faces into a light-weight one for low-resolution face recognition. In our approach, such a cross-dataset resolution-adapted knowledge transfer problem is solved via two-step distillation. In the first step, we conduct cross-dataset distillation to transfer the prior knowledge from private high-resolution faces to public high-resolution faces and generate compact and discriminative features. In the second step, the resolution-adapted distillation is conducted to further transfer the prior knowledge to synthetic low-resolution faces via multi-task learning. By learning low-resolution face representations and mimicking the adapted high-resolution knowledge, a light-weight student model can be constructed with high efficiency and promising accuracy in recognizing low-resolution faces. Experimental results show that the student model performs impressively in recognizing low-resolution faces with only 0.21M parameters and 0.057MB memory. Meanwhile, its speed reaches up to 14,705, ~934 and 763 faces per second on GPU, CPU and mobile phone, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。