Enabling all in-edge deep learning: A literature review

P Joshi, M Hasanuzzaman, C Thapa, H Afli… - IEEE Access, 2023 - ieeexplore.ieee.org
In recent years, deep learning (DL) models have demonstrated remarkable achievements
on non-trivial tasks such as speech recognition, image processing, and natural language …

Forms: Fine-grained polarized reram-based in-situ computation for mixed-signal dnn accelerator

G Yuan, P Behnam, Z Li, A Shafiee… - 2021 ACM/IEEE 48th …, 2021 - ieeexplore.ieee.org
Recent work demonstrated the promise of using resistive random access memory (ReRAM)
as an emerging technology to perform inherently parallel analog domain in-situ matrix …

Compiler-aware neural architecture search for on-mobile real-time super-resolution

Y Wu, Y Gong, P Zhao, Y Li, Z Zhan, W Niu… - … on Computer Vision, 2022 - Springer
Deep learning-based super-resolution (SR) has gained tremendous popularity in recent
years because of its high image quality performance and wide application scenarios …

Pruning via iterative ranking of sensitivity statistics

S Verdenius, M Stol, P Forré - ar** of input-output channels
J Zhu, J Pei - Neurocomputing, 2022 - Elsevier
As the smallest structural unit of feature map**, the convolution kernel in a deep
convolution neural networks (DCNN) convolutional layer is responsible for the input channel …

Target attention deep neural network for infrared image enhancement

D Wang, R Lai, J Guan - Infrared Physics & Technology, 2021 - Elsevier
The inherent high background radiation and low contrast of infrared images severely cripple
the precision of target detection and recognition. However, existing infrared image …

Enabling retrain-free deep neural network pruning using surrogate lagrangian relaxation

D Gurevin - 2022 - search.proquest.com
Network pruning is a widely used technique to reduce computation cost and model size for
deep neural networks. However, the typical three-stage pipeline, ie, training, pruning and …

Design automation for fast, lightweight, and effective deep learning models: A survey

D Zhang, K Chen, Y Zhao, B Yang, L Yao… - arxiv preprint arxiv …, 2022 - arxiv.org
Deep learning technologies have demonstrated remarkable effectiveness in a wide range of
tasks, and deep learning holds the potential to advance a multitude of applications …

All-in-one: A highly representative dnn pruning framework for edge devices with dynamic power management

Y Gong, Z Zhan, P Zhao, Y Wu, C Wu, C Ding… - Proceedings of the 41st …, 2022 - dl.acm.org
During the deployment of deep neural networks (DNNs) on edge devices, many research
efforts are devoted to the limited hardware resource. However, little attention is paid to the …

Moc: Multi-objective mobile cpu-gpu co-optimization for power-efficient dnn inference

Y Wu, Y Gong, Z Zhan, G Yuan, Y Li… - 2023 IEEE/ACM …, 2023 - ieeexplore.ieee.org
With the emergence of DNN applications on mobile devices, plenty of attention has been
attracted to their optimization. However, the impact of DNN inference tasks on device power …