تقرير
Low Power Inference for On-Device Visual Recognition with a Quantization-Friendly Solution
| العنوان: | Low Power Inference for On-Device Visual Recognition with a Quantization-Friendly Solution |
|---|---|
| المؤلفون: | Feng, Chen, Sheng, Tao, Liang, Zhiyu, Zhuo, Shaojie, Zhang, Xiaopeng, Shen, Liang, Ardi, Matthew, Berg, Alexander C., Chen, Yiran, Chen, Bo, Gauen, Kent, Lu, Yung-Hsiang |
| سنة النشر: | 2019 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | The IEEE Low-Power Image Recognition Challenge (LPIRC) is an annual competition started in 2015 that encourages joint hardware and software solutions for computer vision systems with low latency and power. Track 1 of the competition in 2018 focused on the innovation of software solutions with fixed inference engine and hardware. This decision allows participants to submit models online and not worry about building and bringing custom hardware on-site, which attracted a historically large number of submissions. Among the diverse solutions, the winning solution proposed a quantization-friendly framework for MobileNets that achieves an accuracy of 72.67% on the holdout dataset with an average latency of 27ms on a single CPU core of Google Pixel2 phone, which is superior to the best real-time MobileNet models at the time. Comment: Accepted At The 2nd Workshop on Machine Learning on the Phone and other Consumer Devices (MLPCD 2) |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/1903.06791 |
| رقم الأكسشن: | edsarx.1903.06791 |
| قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!