0% Complete
فارسی
Home
/
سیزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
A Comparison between Slimed Network and Pruned Network for Head Pose Estimation
Authors :
Amir Salimiparsa
1
Hadi Veisi
2
Mohammad-shahram Moin
3
1- دانشگاه تهران
2- دانشگاه تهران ٫ دانشکده علوم و فنون نوین
3- پژوهشگاه ارتباطات وفناوری اطلاعات
Keywords :
Head pose estimation،MobileNet،Pruning،Quantization،Deep neural networks
Abstract :
Head pose estimation is a critical problem with a wide range of applications. There are many methods that almost solved head pose estimation problems but they are computationally expensive and not suitable for edge devices and embedded systems. In this paper, a deep learning network based on a modified MobileNetV3 architecture is proposed to reduce the computational cost with results comparable to heavy methods. The proposed method is pruned to achieve even less computational cost and results in a network that is more ideal for edge devices and smartphones. The architecture used is MobileNetV3Small which has more inverted residual blocks, making it able to inherit MobileNetV3Large performance but with less width, followed by dense layers. Pruning is enhanced by estimating layer importance and resource reallocation, in order for the informative layers to be less affected by pruning and also to improve performance. In the experiments, the proposed model performs better than many existing heavies with 3.46 MAE before the pruning and 3.61 MAE after the pruning, even though the model has six times fewer parameters than the others and its inference time is about 7ms.
Papers List
List of archived papers
Sentiment Analysis of the Amazon Customers Using the BiGRU Neural Network Enhanced by Attention Mechanism
Sara Sinan Salman al-Abedi - Keyvan Mohebbi
UltraLearn: Next-Generation CyberSecurity Learning Platform
Saeed Raisi - Saeid Ghasemshirazi - Ghazaleh Shirvani
خوشه بندی شبکههای بیسیم ادهاک مبتنی بر محدودیتهای فازی
پروا کلیبری - کریم صمدزمینی
Architectural Insights: Comparing Weight Stationary and Output Stationary Systolic Arrays for Efficient Computation
Mahdi Kalbasi
مدیریت توأم منابع و خواب ایستگاه پایه مبتنی بر یادگیری تقویتی در شبکه های فوق متراکم با ارتباطات دو طرفه
طاهره رحمتی - بهروز شاهقلی قهفرخی
ارائه راهکاری جهت مقابله با حملات DoS در شبکه های نرم افزارمحور
ویدا هاشمی - احمد بختیاری شهری - رضا جاویدان
An Efficient Link Prediction Method using Community Structures
Dr Hadi Shakibian - Setareh Mokhtari
COVID-19 Image Retrieval Using Siamese Deep Neural Network and Hashing Technique
Farsad Zamani Boroujeni - Doryaneh Hossein Afshari - Fatemeh Mahmoodi
خوشه بندی ویسیلاب های دو آوایی زبان فارسی در کاربرد لب خوانی
مهسا هدایتی پور - دکتر یاسر شکفته - دکتر محسن ابراهیمی مقدم
3D Mesh ONoC: Design of low Insertion Loss and Non-blocking Optical Router and Efficient Routing Algorithm
Sanaz Asadinia - Elham Yaghoubi - Mostafa Sadeghi - Mahdi Mehrabi
more
Samin Hamayesh - Version 42.5.2