Opto-Electronic Engineering, Volume. 51, Issue 7, 240126(2024)
Global pooling residual classification network guided by local attention
Figures & Tables(25)
Fig. 8. Three module structures. (a) Block; (b) M-block; (c) MP-block
Fig. 10. Structure diagrams of three types of network. (a) ResNet34-c; (b) M-MSLENet; (c) MP-MSLENet
Fig. 11. Three type of network iteration accuracies under three datasets.(a) CIFAR-10; (b) CIFAR-100; (c) SVHN
Fig. 12. Three type of network iteration loss under three datasets. (a) CIFAR-10; (b) CIFAR-100; (c) SVHN
Fig. 13. Accuracy of five modules at different iterations. (a) CIFAR-100;(b) STL-10; (c) Imagenette; (d) NWPU-RESISC45
Fig. 14. Channel visualizations under different modules. (a) CA; (b) ECA; (c) GCT; (d) SE; (e) M-APC
Table 1. Dataset
View tableView in ArticleTable 1. Dataset
名称 图像尺寸 分类数 训练集数量 测试集数量 CIFAR-10 32×32 10 50000 10000 CIFAR-100 32×32 100 50000 10000 SVHN 32×32 10 73257 26032 GTSRB 32×32 43 39209 12630 STL-10 96×96 10 5000 8000 Imagenette 320×320 10 7000 3000 NWPU-RESISC45 256×256 45 27000 4500
Table 2. Accuracy of three networks under three datasets
View tableView in ArticleTable 2. Accuracy of three networks under three datasets
网络 CIFAR-10/% CIFAR-100/% SVHN/% ResNet-c 95.38 78.02 96.63 M-MSLENet 95.78 79.33 96.89 MP-MSLENet 96.02 80.42 96.94%
Table 3. Comparison of parameters for four modules
View tableView in ArticleTable 3. Comparison of parameters for four modules
网络 准确率/% F1-score Xentropy MSLENet18 79.14 0.7916 0.012 MSLENet34 80.42 0.8065 0.008 MSLENet50 78.66 0.7883 0.010 MSLENet101 79.65 0.7965 0.008
Table 4. Comparison of parameters for five modules on CIFAR-100
View tableView in ArticleTable 4. Comparison of parameters for five modules on CIFAR-100
网络 准确率/% F1-score Xentropy +CA 78.55 0.7881 0.010 +ECA 79.33 0.7949 0.011 +GCT 77.08 0.7810 0.012 +SE 79.25 0.7932 0.010 +MSLE 80.37 0.8054 0.009
Table 5. Comparison of parameters for five modules on STL-10
View tableView in ArticleTable 5. Comparison of parameters for five modules on STL-10
网络 准确率/% F1-score Xentropy +CA 72.25 0.7228 0.005 +ECA 72.40 0.7241 0.006 +GCT 69.26 0.6931 0.008 +SE 70.32 0.7040 0.007 +MSLE 72.78 0.7282 0.003
Table 6. Comparison of parameters for five modules on Imagenette
View tableView in ArticleTable 6. Comparison of parameters for five modules on Imagenette
网络 准确率/% F1-score Xentropy +CA 89.14 0.8924 0.003 +ECA 88.87 0.8903 0.004 +GCT 87.34 0.8745 0.002 +SE 89.07 0.8907 0.003 +MSLE 89.70 0.8991 0.002
Table 7. Comparison of parameters for five modules on NWPU-RESISC45
View tableView in ArticleTable 7. Comparison of parameters for five modules on NWPU-RESISC45
网络 准确率/% F1-score Xentropy +CA 93.00 0.9302 0.012 +ECA 95.33 0.9533 0.003 +GCT 94.20 0.9421 0.007 +SE 95.13 0.9513 0.003 +MSLE 95.40 0.9540 0.004
Table 8. Setting values of hyperparameters during training process
View tableView in ArticleTable 8. Setting values of hyperparameters during training process
超参数 设定值 Input size 32×32 RandomCrop 4 RandomHorizontalFlip 0.5 RandomErasing 0.2 epochs 300 优化器 SGD lr 0.1 lr decay 0.2 batch size 128 Momentum 0.9 Weight decay 5e-4 Mixup 0.2 EMA 0.9 Label Smoothing 0.1 k [4,2,0,0] l 16
Table 9. Classification accuracy of each network under three datasets
View tableView in ArticleTable 9. Classification accuracy of each network under three datasets
网络 CIFAR-10/% CIFAR-100/% SVHN/% VGG-16 91.79 67.84 - SENet 95.22 73.22 87.06 DenseNet-121 94.55 77.01 95.83 CAPR-DenseNet 94.24 78.84 94.95 MobileNetV2 93.37 68.08 - ShuffleNet 89.40 70.06 - ResNet34 87.89 69.41 91.51 Multi-ResNet 94.65 78.68 - EfficientNet 94.01 75.96 93.32 SSE-GAN 85.14 - 92.92 Couplformer 93.54 73.92 94.26 ResNet50+SPAM - 80.53 - FAVOR+ 91.42 72.56 93.21 ResNet-CE 94.27 76.15 - MMA-CCT-7/3×2 94.74 77.5 94.26 CaiT 94.91 79.89 -- Swin-T 94.46 78.07 -- MSLENet 96.93 82.28 97.22
Table 10. FLOPs and params of various networks
View tableView in ArticleTable 10. FLOPs and params of various networks
网络 Params/M FLOPs/G Wide-ResNet 37.16 5.96 ConvNext 27.80 1.45 EfficientNet 52.98 1.49 Swim-T 86.78 4.25 Multi-ResNet 51.23 3.13 MSLENet 22.35 1.20
Table 11. Experimental results of various networks
View tableView in ArticleTable 11. Experimental results of various networks
网络 CIFAR-10/% CIFAR-100/% GTSRB/% NWPU-RESISC45/% Net_2_2_0_0 96.81 79.65 97.26 95.17 Net_4_2_0_0 96.93 82.28 97.39 95.40 Net_4_2_2_0 96.80 82.23 97.13 95.44 Net_8_4_2_0 96.90 82.51 97.27 95.15
Tools
Get Citation
Copy Citation Text
Wentao Jiang, Rui Dong, Shengchong Zhang. Global pooling residual classification network guided by local attention[J]. Opto-Electronic Engineering, 2024, 51(7): 240126
Paper Information
Category: Article
Received: May. 28, 2024
Accepted: Aug. 5, 2024
Published Online: Nov. 12, 2024
The Author Email: Rui Dong (董睿)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20