Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices
arXiv:2106.15304
Abstract
The rapid development of autonomous driving, abnormal behavior detection, and behavior recognition makes an increasing demand for multi-person pose estimation-based applications, especially on mobile platforms. However, to achieve high accuracy, state-of-the-art methods tend to have a large model size and complex post-processing algorithm, which costs intense computation and long end-to-end latency. To solve this problem, we propose an architecture optimization and weight pruning framework to accelerate inference of multi-person pose estimation on mobile devices. With our optimization framework, we achieve up to 2.51x faster model inference speed with higher accuracy compared to representative lightweight multi-person pose estimator.
References in corpus (5)
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
- Real-Time Execution of Large-scale Language Models on Mobile
- Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
- EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation