Opto-Electronic Engineering, Volume. 51, Issue 5, 240050(2024)
Sparse feature image classification network with spatial position correction
Figures & Tables(20)
Fig. 2. Comparison of convolution operations before and after modifying the size of the first layer convolution kernel
Fig. 7. Three types of residual blocks. (a) Basic block；(b) Residual block；(c) APM
Fig. 8. The arrangement of APM-Block and SSEF module positions and quantities
Fig. 9. Influence of different convolutional kernel sizes on classification accuracy
Fig. 10. Influence of different learning rates on classification accuracy
Fig. 12. Classification accuracy of each network on different datasets. (a) CIFAR-10;(b) CIFAR-100; (c) SVHN; (d) Imageneete
Table 1. Accuracy under different N values
View tableView in ArticleTable 1. Accuracy under different N values
N 24 32 64 128 ACC/% 72.19 76.53 78.91 77.78
Table 2. Experimental datasets
View tableView in ArticleTable 2. Experimental datasets
Dataset Size Classification Trainset Testset CIFAR-10 32×32 10 50000 10000 CIFAR-100 32×32 100 50000 10000 SVHN 32×32 10 73257 26032 Imagenette 224×224 10 9469 3925 Imagewoof 224×224 10 9025 3929
Table 3. Influence of different positions and numbers of SSEF modules and APM-Blocks on classification accuracy
View tableView in ArticleTable 3. Influence of different positions and numbers of SSEF modules and APM-Blocks on classification accuracy
CIFAR-10/% CIFAR-100/% SVHN/% Imagenette/% Imagewoof/% A 94.79 77.22 95.63 86.76 80.56 B 95.19 77.86 96.37 87.17 81.17 C 95.13 77.63 96.25 87.09 80.86 D 95.27 78.03 96.35 87.12 81.06 E 95.89 78.79 96.97 87.79 81.35 F 95.76 78.57 96.56 87.64 81.29 G 95.69 78.63 96.89 87.72 81.41 H 96.72 80.63 97.43 88.75 82.09 I 96.37 80.12 97.26 88.39 81.71 J 96.13 79.81 97.19 88.27 81.63 K 96.46 80.52 97.31 88.51 81.76
Table 4. The impact of SSEF module on parameters and accuracy
View tableView in ArticleTable 4. The impact of SSEF module on parameters and accuracy
Module Param ACC/% Loss S1 45696 78.12 0.82 S2 45696 78.53 0.79 S3 49920 78.19 0.81 SSEF 13504 78.96 0.76
Table 5. The impact of parameters reduction on computational efficiency under different networks
View tableView in ArticleTable 5. The impact of parameters reduction on computational efficiency under different networks
Network Speed/(f/s) Params/M FLOPs/G ACC/% Multi-ResNet[ 22 ]1.62 51.23 37.93 78.68 ResNet-PSE[ 16 ]2.23 40.56 27.56 72.81 ResNeXt-PSE[ 16 ]2.07 47.29 31.34 77.32 SSLLNet[ 23 ]2.57 31.57 20.86 79.23 ATONet[ 24 ]2.88 30.12 16.91 78.54 SSCNet 3.05 21.36 11.71 80.63
Table 6. Ablation experiments between different modules on different datasets
View tableView in ArticleTable 6. Ablation experiments between different modules on different datasets
Group SPCS SSEF APM ACC1/% ACC2/% ACC3/% ACC4/% Speed/ (f/s) FLOPs/G 1 - √ √ 90.23 69.63 92.89 83.67 2.85 13.93 2 √ - √ 92.36 75.51 94.17 85.23 2.32 26.67 3 √ √ - 95.67 77.34 96.56 87.09 2.96 12.36 4 √ √ √ 96.72 80.63 97.43 88.75 3.05 11.17
Table 7. Different metrics for each network on five datasets
View tableView in ArticleTable 7. Different metrics for each network on five datasets
Network CIFAR10 CIFAR-100/% SVHN Imagenette/% Imagewoof/% Speed/(f/s) Params/M FLOPs/G ResNet-34[ 5 ]87.82 68.92 91.39 84.91 78.86 3.02 21.32 11.63 HO-ResNet[ 10 ]96.32 77.12 95.69 86.23 79.64 1.93 50.26 35.69 CAPRDenseNet[ 25 ]94.24 78.84 94.95 87.56 80.79 2.86 25.51 17.73 MobileNet-LAM[ 18 ]89.37 68.09 ------ ------ ------ ------ ------ ------ Multi-ResNet[ 22 ]94.56 78.68 94.58 87.69 81.21 1.62 51.23 37.93 Couplformer[ 26 ]93.54 73.92 94.26 85.13 79.08 2.73 27.63 14.29 ResNet-PSE[ 16 ]92.89 72.81 96.14 85.09 79.13 2.23 40.56 27.56 ResNeXt-PSE[ 16 ]93.92 77.32 96.54 86.27 80.66 2.07 47.29 31.34 ATONet[ 24 ]94.51 78.54 95.21 86.67 80.19 2.88 30.12 16.91 QKFormer[ 27 ]96.18 80.26 97.13 88.32 81.65 2.36 35.62 26.39 TLENet[ 28 ]95.46 78.42 96.83 87.62 80.57 2.19 46.67 30.57 SSLLNet[ 23 ]95.51 79.23 96.91 87.93 80.89 2.57 31.57 20.86 SSCNet 96.72 80.63 97.43 88.75 82.09 3.05 21.36 11.71
Tools
Get Citation
Copy Citation Text
Wentao Jiang, Chen Chen, Shengchong Zhang. Sparse feature image classification network with spatial position correction[J]. Opto-Electronic Engineering, 2024, 51(5): 240050
Paper Information
Category: Article
Received: Mar. 6, 2024
Accepted: Apr. 24, 2024
Published Online: Jul. 31, 2024
The Author Email: Chen Chen (陈晨)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20