Convolutional wavelet blocks in image classification

U. A. Varabei ; A. È. Malevich

Journal of the Belarusian State University. Mathematics and Informatics, Tome 2 (2024), pp. 93-103.

Résumé

In this paper, based on an image classification problem and wavelet family $CDF-9/7$, it is shown how to incorporate discrete wavelet transform into a computer vision model, while maintaining the ability of its training with the backpropagation method. A convolutional wavelet block, that extracts features at different levels of decomposition of the incoming signal, is proposed and successfully integrated into a set of neural network models. The blocks implemented allow to reduce the original model size by $30-40 \%$, while maintaining comparable quality in terms of metric. An effective method for evaluation of discrete wavelet transform on graphics processing unit with lifting scheme is presented. The implementation of wavelet blocks uses element-wise operations of additions and multiplications, thus allowing a simple export of a trained model into one of desired formats for running on new data. $ResNetV2-50$, $MobileNetV2$ and $EfficientNetV2-B0$ architectures are used as the basis models. A new dataset, which is based on a set of categories of LSUN dataset, is constructed for conducting experiments.

Détail

Keywords: neural networks; deep learning; wavelets; discrete wavelet transform; image classification

Bibliographie

[1] K. Simonyan, A. Zisserman, “Very deep convolutional networks for large-scale image recognition”, arXiv, 2015, 14 | DOI

[2] K. He, X. Zhang, S. Ren, J. Sun, “Deep residual learning for image recognition”, arXiv, 2015, 12 | DOI

[3] M. Tan, Q. V. Le, “EfficientNet: rethinking model scaling for convolutional neural networks”, arXiv, 2020, 11 | DOI

[4] H. Cheng, M. Zhang, J. Q. Shi, “A survey on deep neural network pruning-taxonomy, comparison, analysis, and recommendations”, arXiv, 2023, 23 | DOI

[5] C. Blake, D. Orr, C. Luschi, “Unit scaling: out-of-the-box low-precision training”, arXiv, 2023, 29 | DOI

[6] Shuai. Zhang, M. a. Guangdi, Weichen. Yang, Zuo. Fang, S. V. Ablameyko, “Car parking detection in images by using a semi-supervised modified YOLOv5 model”, Journal of the Belarusian State University. Mathematics and Informatics, 3 (2023), 72–81

[7] A. Singh, N. Kingsbury, “Efficient convolutional network learning using parametric log based dual-tree wavelet ScatterNet”, arXiv, 2017, 8 | DOI

[8] Q. Li, L. Shen, S. Guo, Z. Lai, “Wavelet integrated CNNs for noise-robust image classification”, arXiv, 2020, 17 | DOI

[9] M. Wolter, F. Blanke, R. Heese, J. Garcke, “Wavelet-packets for deepfake image analysis and detection”, arXiv, 2022, 29 | DOI

[10] K. He, X. Zhang, S. Ren, J. Sun, “Identity mappings in deep residual networks”, arXiv, 2016, 15 | DOI

[11] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L-C. Chen, “MobileNetV2: interested residuals and linear bottlenecks”, arXiv, 2019, 14 | DOI

[12] M. Tan, Q. V. Le, “EfficientNetV2: smaller models and faster training”, arXiv, 2021, 11 | DOI

[13] U. Lepik, H. Hein, Haar wavelets: with applications, Mathematical engineering, Springer, Cham, 2014, X+207 pp. | DOI

[14] I. Daubechies, Ten lectures on wavelets, CBMSNSF regional conference series in applied mathematics, volume 61, Society for Industrial and Applied Mathematics, Philadelphia, 1992, XIX+357 pp.

[15] A. Cohen, I. Daubechies, J. C. Feauveau, “Biorthogonal bases of compactly supported wavelets”, Communications on Pure and Applied Mathematics, 45(5) (1992), 485–560 | DOI

[16] F. Yu, A. Seff, Y. Zhang, S. Song, T. Funkhouser, J. Xiao, “LSUN: construction of a large-scale image dataset using deep learning with humans in the loop”, arXiv, 2016, 9 | DOI