Optimization and Practice of Convolutional Neural Networks in Image Classification Tasks
This study focuses on the optimization and practice of Convolutional Neural Networks (CNN) in image classification tasks. A deep neural network model was constructed by introducing the CBAM (Convolutional Block Attention Module) attention mechanism and residual structure. This model combines the stability of residual networks during training with the advantages of CBAM in feature extraction, aiming to improve image classification performance. The experiment used the CIFAR-10 dataset and achieved a testing accuracy of 86% through optimization methods such as data augmentation, batch normalization, reasonable control of the number of fully connected layers, and exponential decay learning rate strategy. The study also explored the effects of data augmentation, batch normalization layer utility, fully connected layer quantity control, residual structure effectiveness, and CBAM attention mechanism on model performance, providing valuable insights for optimizing CNN in image classification tasks.
References
- Zhu Junyu Technical Analysis of Image Recognition Based on Convolutional Neural Networks [J]. Changjiang Information and Communication, 2023, 36 (08): 66-68
- Li Wenjing, Bai Jing, Peng Bin, Yang Zhanyuan Overview of Graph Convolutional Neural Networks and Their Applications in Image Recognition [J]. Computer Engineering and Applications, 2023, 59 (22): 15-35
- Dou Hui, Zhang Lingming, Han Feng, Shen Fufu, Zhao Jian A review of interpretability research on convolutional neural networks [J]. Journal of Software, 2024, 35 (01): 159-184
- Zhang Ke, Feng Xiaohan, Guo Yurong, Su Yukun, Zhao Kai, Zhao Zhenbing, Ma Zhanyu, Ding Qiaolin A Review of Deep Convolutional Neural Network Models for Image Classification [J]. Chinese Journal of Image and Graphics, 2021, 26 (10): 2305-2325
- Wei Xiushen Analytical Deep Learning [M]. Electronic Industry Press: 201811.200