[PDF][PDF] 轻量化卷积神经网络在船舶分类中的应用

王文亮, 杨晓迪, 张博雅, 马吉顺, 曾鹏… - Laser & Optoelectronics …, 2023 - researching.cn
摘要为权衡船舶分类模型的分类精度和模型大小, 提出一种改进GhostNet-50
的轻量化卷积神经网络AGNet 对自制的船舶数据集进行分类. 首先, 提出一种融合非对称卷积的 …

Improved model based on GoogLeNet and residual neural network ResNet

X Huang - International Journal of Cognitive Informatics and …, 2022 - igi-global.com
To improve the accuracy of image classification, a kind of improved model is proposed. The
shortcut is added to GoogLeNet inception v1 and several other ways of shortcut are given …

多通路轻量化卷积神经网络的研究.

赵立欣, 白宇, 安胜彪 - Journal of Computer Engineering & …, 2023 - search.ebscohost.com
大量研究表明, 卷积神经网络宽度展宽可以提取更加多元的特征, 但对模型通道宽度进行展宽时,
引起训练参数量呈二次增长, 进而导致训练成本高与网络模型庞大的问题. 针对上述问题 …

[PDF][PDF] Lightweight network study of leather defect segmentation with Kronecker product multipath decoding

Z Zhang, Y Fu, H Huang, F Rao… - Mathematical Biosciences …, 2022 - aimspress.com
In the leather production process, defects on the leather surface are a key factor in the
quality of the finished leather. Leather defect detection is an important step in the leather …

[PDF][PDF] A Compact Depth Separable Convolutional Image Filter for Clinical Color Perception Test

Z Wen, C Ye, M Zhao, FCO Yang - Journal of Internet Technology, 2024 - jit.ndhu.edu.tw
Deep convolutional neural networks have achieved good performance in the application of
computer vision, but there are also problems, such as a large amount of computation, time …