Pruning for compression of visual pattern recognition networks: a survey from deep neural networks perspective

SA Bhalgaonkar, MV Munot, AD Anuse - Pattern recognition and data …, 2022 - Springer
Abstract Visual Pattern Recognition Networks (VPRN) delivers high performance using deep
neural networks. With the advancements in deep neural networks VPR network has gained …

QuickLoc: adaptive deep-learning for fast indoor localization with mobile devices

S Tiku, P Kale, S Pasricha - ACM Transactions on Cyber-Physical …, 2021 - dl.acm.org
Indoor localization services are a crucial aspect for the realization of smart cyber-physical
systems within cities of the future. Such services are poised to reinvent the process of …

A theoretical framework towards building a lightweight model for pothole detection using knowledge distillation approach

A Musa, M Hamada, M Hassan - SHS Web of Conferences, 2022 - shs-conferences.org
Despite recent advances in deep learning, the rise of edge devices, and the exponential
growth of Internet of Things (IoT) connected devices undermine the performance of deep …

[PDF][PDF] The compression techniques applied on deep learning model

H He, L Huang, Z Huang… - Highlights in Science …, 2022 - pdfs.semanticscholar.org
In recent years, the penetration rate of smartphones has gradually completed, artificial
intelligence is the cutting-edge technology that can trigger disruptive changes. Deep …

Toward real-time indoor localization with smartphones with conditional deep learning

S Tiku, P Kale, S Pasricha - Machine Learning for Indoor Localization and …, 2023 - Springer
Indoor localization services are a crucial aspect for the realization of smart cyber-physical
systems within cities of the future. Such services are poised to reinvent the process of …

Image distillation based screening for x-ray crystallography diffraction images

L Chen, K Xu, X Zheng, Y Zhu… - … IEEE intl conf on parallel & …, 2021 - ieeexplore.ieee.org
The modern synchrotron radiation facilities are producing massive diffraction images, which
present a severe problem for data processing due to the high dimensionality of imaging …

[PDF][PDF] Knowledge distillation for face recognition on lightweight neural networks

L Gertz, A Lindmark - 2021 - odr.chalmers.se
Face recognition is a common biometric used in everyday commercial products and is also
widely used in safety and surveillance. Accuracy is critical when face recognition is used for …