Edge applications, such as collaborative robotics and spacecraft rendezvous, demand efficient 6D object pose estimation on resource-constrained embedded platforms. Existing 6D pose estimation networks are often too large for such deployments, necessitating compression while maintaining reliable performance. To address this challenge, we introduce Modular Quantization-Aware Training (MQAT), an adaptive and mixed-precision quantization-aware training strategy that exploits the modular structure of modern 6D pose estimation architectures. MQAT guides a systematic gradated modular quantization sequence and determines module-specific bit precisions, leading to quantized models that outperform those produced by state-of-the-art uniform and mixed-precision quantization techniques. Our experiments showcase the generality of MQAT across datasets, architectures, and quantization algorithms. Remarkably, MQAT-trained quantized models achieve a significant accuracy boost (>7%) over the baseline full-precision network while reducing model size by a factor of 4x or more. Our project website is at: https://saqibjaved1.github.io/MQAT_/
@article{arxiv.2303.06753,
title = {Modular Quantization-Aware Training for 6D Object Pose Estimation},
author = {Saqib Javed and Chengkun Li and Andrew Price and Yinlin Hu and Mathieu Salzmann},
journal= {arXiv preprint arXiv:2303.06753},
year = {2024}
}
Comments
Accepted to Transactions on Machine Learning Research (TMLR), 2024