Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
Pose estimation plays a critical role in human-centered vision applications. However, it is difficult to deploy state-of-the-art HRNet-based pose estimation models on resource-constrained edge devices due to the high computational cost (more than 150 GMACs per frame). In this paper, we study efficient architecture design for real-time multi-person pose estimation on edge. We reveal that HRNet's high-resolution branches are redundant for models at the low-computation region via our gradual shrinking experiments. Removing them improves both efficiency and performance. Inspired by this finding, we design LitePose, an efficient single-branch architecture for pose estimation, and introduce two simple approaches to enhance the capacity of LitePose, including Fusion Deconv Head and Large Kernel Convs. Fusion Deconv Head removes the redundancy in high-resolution branches, allowing scale-aware feature fusion with low overhead. Large Kernel Convs significantly improve the model's capacity and receptive field while maintaining a low computational cost. With only 25% computation increment, 7x7 kernels achieve +14.0 mAP better than 3x3 kernels on the CrowdPose dataset. On mobile platforms, LitePose reduces the latency by up to 5.0x without sacrificing performance, compared with prior state-of-the-art efficient pose estimation models, pushing the frontier of real-time multi-person pose estimation on edge. Our code and pre-trained models are released at https://github.com/mit-han-lab/litepose.
Code (1)
Tasks
2D Human Pose EstimationMulti-Person Pose EstimationPose EstimationSimilar Papers 제목 키워드 기반
A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems
Large Language Models-Cognitive Assistants (LLM-CAs) can enhance Quality Management Systems (QMS) in manufacturing, fostering continuous process improvement and knowledge management. However, there is no human-centred so…
Look Into the LITE in Deep Learning for Time Series Classification
Deep learning models have been shown to be a powerful solution for Time Series Classification (TSC). State-of-the-art architectures, while producing promising results on the UCR and the UEA archives , present a high numb…
Time SeriesTime Series ClassificationRoles of LLMs in the Overall Mental Architecture
To better understand existing LLMs, we may examine the human mental (cognitive/psychological) architecture, and its components and structures. Based on psychological, philosophical, and cognitive science literatures, it …
The Case for a Mixed-Initiative Collaborative Neuroevolution Approach
It is clear that the current attempts at using algorithms to create artificial neural networks have had mixed success at best when it comes to creating large networks and/or complex behavior. This should not be unexpecte…
Common Sense ReasoningGame DesignIngenuityAn Abstract Architecture for Explainable Autonomy in Hazardous Environments
Autonomous robotic systems are being proposed for use in hazardous environments, often to reduce the risks to human workers. In the immediate future, it is likely that human workers will continue to use and direct these …