Gradient - Based Convolutional Neural Network Feature Visualization
DOI:
https://doi.org/10.53469/wjimt.2024.07(02).08Keywords:
Convolutional neural network, Robustness, Feature visualizationAbstract
This paper proposes a novel method for evaluating the robustness of visualization. In terms of effectiveness, the paper assesses visual coherence, visual resolution, and multi-target visualization. Regarding the robustness of visualization methods, a new evaluation approach is introduced by applying the model's adversarial resistance assessment from image classification to visualization methods. The paper incorporates deconvolution techniques to showcase image features extracted by different convolutional layers of Convolutional Neural Networks (CNN) and employs class activation techniques to visualize critical regions influencing CNN decisions. Additionally, for multi-target input images, a gradient-class activation-based visualization method is proposed and compared across different models, demonstrating its applicability to any model and its superior ability to retain target information compared to other visualization methods. Finally, the paper introduces an evaluation method for visualization effects, focusing on both effectiveness and robustness. In practical applications, this work provides valuable insights for the interpretability of deep learning models and handling complex scenarios.
References
Cao, Kelei, et al. "Analyzing the noise robustness of deep neural networks." IEEE Transactions on Visualization and Computer Graphics 27.7 (2020): 3289-3304.
Becker, Martin, et al. "Robust dimensionality reduction for data visualization with deep neural networks." Graphical Models 108 (2020): 101060.
Lou, Yang, et al. "A convolutional neural network approach to predicting network connectedness robustness." IEEE Transactions on Network Science and Engineering 8.4 (2021): 3209-3219.
Shao, Rulin, et al. "On the adversarial robustness of vision transformers." ar**v preprint ar**v:2103.15670 (2021).
Wang, Zijie J., et al. "CNN explainer: learning convolutional neural networks with interactive visualization." IEEE Transactions on Visualization and Computer Graphics 27.2 (2020): 1396-1406.
Tang, Haihong, et al. "A novel convolutional neural network for low-speed structural fault diagnosis under different operating condition and its understanding via visualization." IEEE Transactions on Instrumentation and Measurement 70 (2020): 1-11.
Chen, Junbin, et al. "Multiscale convolutional neural network with feature alignment for bearing fault diagnosis." IEEE Transactions on Instrumentation and Measurement 70 (2021): 1-10.
Wang, Huan, et al. "Attention-guided joint learning CNN with noise robustness for bearing fault diagnosis and vibration signal denoising." ISA transactions 128 (2022): 470-484.
Zhao, Wenlei, et al. "Multiscale inverted residual convolutional neural network for intelligent diagnosis of bearings under variable load condition." Measurement 188 (2022): 110511.
Fang, Hairui, et al. "LEFE-Net: A lightweight efficient feature extraction network with strong robustness for bearing fault diagnosis." IEEE Transactions on Instrumentation and Measurement 70 (2021): 1-11.
Dyrba, Martin, et al. "Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease." Alzheimer's research & therapy 13 (2021): 1-18.
Pandey, Akshay, and Kamal Jain. "A robust deep attention dense convolutional neural network for plant leaf disease identification and classification from smart phone captured real world images." Ecological Informatics 70 (2022): 101725.
Zhang, Qi, et al. "Integrated neural networks based on feature fusion for underwater target recognition." Applied Acoustics 182 (2021): 108261.
Ding, Z., E. Pascal, and M. De Graef. "Indexing of electron back-scatter diffraction patterns using a convolutional neural network." Acta Materialia 199 (2020): 370-382.
Jang, Ho**, and Frank Tong. "Improved modeling of human vision by incorporating robustness to blur in convolutional neural networks." Nature Communications 15.1 (2024): 1989.