Jeongun Jin, Seongchan Park, Shinhyup Lee, Seunghyun Lee, Soonchul Kwon
언어
영어(ENG)
URL
https://www.earticle.net/Article/A486491
※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.
원문정보
초록
영어
Post-Training Quantization (PTQ), a method for model quantization without the need for retraining, is under active investigation for the deployment of real-time human pose estimation techniques on resourceconstrained edge devices. However, conventional PTQ techniques exhibit a critical limitation when applied to the SimCC output format utilized by the RTMPose model, leading to severe performance degradation due to the high sensitivity of its coordinate representation. This study proposes an optimization framework to overcome this challenge by systematically identifying optimal quantization targets through a Singular Value Decomposition (SVD)-based sensitivity analysis and by correcting the distorted output distribution via realtime post-processing. Experimental results demonstrate that the proposed framework achieves a 1.56-fold model compression while successfully retaining 88.8% of the accuracy of the original FP32 model. This research is anticipated to significantly enhance the practical deployment of models with sensitive output architectures, such as RTMPose, thereby contributing to a wide range of applications in real-time human pose estimation.
목차
Abstract 1. Introduction 2. Background and Related Work 3. Proposed RTMPose Optimization Method 3.1 Overall Optimization Pipeline 3.2 SVD-based Quantization Sensitivity Analysis 3.3 Distribution Correction Technique 4. Experiments and Results 4.1 Experimental Environment 4.2 Evaluation Metrics 4.3 Experimental Results 5. Discussion and Conclusion Acknowledgement Reference