Vehicle classification model based on depthwise separable convolution and ICBAM.

<p>Vehicle classification model based on depthwise separable convolution and ICBAM.</p>

Saved in:

Bibliographic Details
Main Author:	Qifeng Niu (22662531) (author)
Other Authors:	Jinhui Han (8786483) (author), Zhen Sui (22662534) (author), Feng Xu (89016) (author)
Published:	2025
Subjects:	Biotechnology Space Science Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified spatial attention modules scale feature extraction model &# 8217 introducing dropout regularization intelligent transportation systems five classic models feature weighting strategies depthwise separable convolutions decomposing convolution operations constrained deployment scenarios class feature representation 286 test samples 060 test samples two key components stanford cars dataset overall lightweight structure experimental results demonstrate dsc module reduces channel attention module average classification accuracy high computational complexity computational complexity tcd dataset results underscore key regions high demands experimental evaluations classification outcomes computational efficiency weight distribution traditional cbam study proposes requirements due practical value practical applications potential applicability maintain consistency limited generalization interaction mechanisms including alexnet icbam enhances icbam addresses icbam ). core task cam visualizations accurate multi 51 %. 36 %,
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items