Image Classification Algorithm Based on Classification Activation Map Enhancement
Classification activation map (CAM) has problems such as sparseness, discontinuity, incompleteness, etc.,and most of the current research only uses it for visual analysis. Based on this, this paper firstly utilizes the dilated convolution to design an automatic weighted multi-scale feature learning...
Main Author: | YANG Menglin, ZHANG Wensheng |
---|---|
Format: | Article |
Language: | zho |
Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2020-01-01
|
Series: | Jisuanji kexue yu tansuo |
Subjects: | |
Online Access: | http://fcst.ceaj.org/CN/abstract/abstract2096.shtml |
Similar Items
-
Influence of image classification accuracy on saliency map estimation
by: Taiki Oyama, et al.
Published: (2018-10-01) -
Deep Learning Based Mineral Image Classification Combined With Visual Attention Mechanism
by: Yang Liu, et al.
Published: (2021-01-01) -
Coffee Disease Visualization and Classification
by: Milkisa Yebasse, et al.
Published: (2021-06-01) -
Development, improvement and assessment of image classification and probability mapping algorithms
by: Wang, Qing
Published: (2018) -
Multiscale Superpixel-Based Sparse Representation for Hyperspectral Image Classification †
by: Shuzhen Zhang, et al.
Published: (2017-02-01)