GSB: Group superposition binarization for vision transformer with limited training samples
Abstract Vision Transformer (ViT) has performed remarkably in various computer vision
tasks. Nonetheless, affected by the massive amount of parameters, ViT usually suffers from …
tasks. Nonetheless, affected by the massive amount of parameters, ViT usually suffers from …
BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices
Y Xu, Y Lee, G Yi, B Liu, Y Chen, P Liu, J Wu… - arXiv preprint arXiv …, 2024 - arxiv.org
Deep neural networks (DNNs) are powerful for cognitive tasks such as image classification,
object detection, and scene segmentation. One drawback however is the significant high …
object detection, and scene segmentation. One drawback however is the significant high …
适应于硬件部署的神经网络剪枝量化算法
王鹏， 张嘉诚， 范毓洋 - 计算机工程与科学, 2024 - joces.nudt.edu.cn
深度神经网络由于性能优异已经在图像识别, 目标检测等领域广泛应用, 然而其包含大量参数和
巨大计算量, 导致在需要低延时和低功耗的移动边缘端部署时困难. 针对该问题 …
巨大计算量, 导致在需要低延时和低功耗的移动边缘端部署时困难. 针对该问题 …
Gradient Estimation for Ultra Low Precision POT and Additive POT Quantization
Deep learning networks achieve high accuracy for many classification tasks in computer
vision and natural language processing. As these models are usually over-parameterized …
vision and natural language processing. As these models are usually over-parameterized …
Arithmetic for Deep Learning
F de Dinechin, M Kumm - … -Specific Arithmetic: Computing Just Right for the …, 2023 - Springer
Abstract Machine learning has an ever increasing impact on many applications. This chapter
studies the specific arithmetic requirements of deep neural networks (DNNs). The underlying …
studies the specific arithmetic requirements of deep neural networks (DNNs). The underlying …
A neural network pruning and quantization algorithm for hardware deployment
P WANG, J ZHANG, Y FAN - Computer Engineering & Science, 2024 - joces.nudt.edu.cn
Due to their superior performance, deep neural networks have been widely applied in fields
such as image recognition and object detection. However, they contain a large number of …
such as image recognition and object detection. However, they contain a large number of …