A Lattice-Structure-Based Trainable Orthogonal Wavelet Unit for Image Classification

Abstract

This work introduces Orthogonal Lattice Universal Wavelet Unit, a novel trainable wavelet unit to enhance image classification and anomaly detection in convolutional neural networks by reducing information loss during pooling. The unit employs an orthogonal lattice structure, relaxing the zero-at- $\pi $ condition and decreasing the number of trainable wavelet coefficients. This innovation is a key novelty of the work. The unit modifies convolution, pooling, and down-sampling operations. Implemented in residual neural networks with 18 layers, it improved detection accuracy on CIFAR10 (by 2.67%), ImageNet1K (by 1.85%), and the Describable Textures dataset (by 9.52%), showcasing its advantages in detecting detailed features. Similar gains were seen in the implementations for residual neural networks with 34 layers and 50 layers. For anomaly detection in hazelnut images on the MVTec Anomaly Detection dataset, the proposed method achieved a segmentation area under the receiver operating characteristic curve of 97.15% and better anomaly localization. The method excels in detecting detailed features, despite increased trainable parameters from using one-layer fully convolutional networks for feature combination.

Keywords

• Anomaly detection
• computer vision
• discrete wavelet transforms
• feature extraction
• image processing
• image recognition