Geodesic
Large-scale Image Classification with Multi-perspective Deep Transfer Learning
Computer Science and Information Systems, Tome 20 (2023) no. 2.

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

Most research efforts on image classification so far have been focused on medium-scale datasets. In addition, there exist other problems, such as difficulty in feature extraction and small sample size. In order to address above difficulties, this paper proposes a multi-perspective convolutional neural network model, which contains channel attention module and spatial attention module. The proposed modules derive attention graphs from channel dimension and spatial dimension respectively, then the input features are selectively learned according to the importance of the features. We explain how the gain in storage can be traded against a loss in accuracy and/or an increase in CPU cost. In addition, we give the interpretability of the model at multiple scales. Quantitative and qualitative experimental results demonstrate that the accuracy of our proposed model can be improved by up to 3.8% and outperforms the state-of-the-art methods.
Keywords: large-scale image classification, channel attention module, spatial attention module, interpretability of the model, multiple scales 
@article{CSIS_2023_20_2_a10,
     author = {Bin Wu and Tao Zhang and Li Mao},
     title = {Large-scale {Image} {Classification} with {Multi-perspective} {Deep} {Transfer} {Learning}},
     journal = {Computer Science and Information Systems},
     publisher = {mathdoc},
     volume = {20},
     number = {2},
     year = {2023},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2023_20_2_a10/}
}
TY  - JOUR
AU  - Bin Wu
AU  - Tao Zhang
AU  - Li Mao
TI  - Large-scale Image Classification with Multi-perspective Deep Transfer Learning
JO  - Computer Science and Information Systems
PY  - 2023
VL  - 20
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/CSIS_2023_20_2_a10/
ID  - CSIS_2023_20_2_a10
ER  - 
%0 Journal Article
%A Bin Wu
%A Tao Zhang
%A Li Mao
%T Large-scale Image Classification with Multi-perspective Deep Transfer Learning
%J Computer Science and Information Systems
%D 2023
%V 20
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/CSIS_2023_20_2_a10/
%F CSIS_2023_20_2_a10
Bin Wu; Tao Zhang; Li Mao. Large-scale Image Classification with Multi-perspective Deep Transfer Learning. Computer Science and Information Systems, Tome 20 (2023) no. 2. http://geodesic.mathdoc.fr/item/CSIS_2023_20_2_a10/