Work

Biorthogonal Lattice Tunable Wavelet Units and Their Implementation in Convolutional Neural Networks for Computer Vision Problems

Year: 2025

Type: article

Abstract: This work introduces a universal wavelet unit constructed with a biorthogonal lattice structure which is a novel tunable wavelet unit to enhance image classification and anomaly detection in convolutional neural networks by reducing information loss during pooling. The unit employs a biorthogonal lattice structure to modify 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 11.81%), showcasing its advantages in detecting detailed features. Similar gains are achieved in the implementations for residual neural networks with 34 layers and 50 layers. For anomaly detection on the MVTec Anomaly Detection and TUKPCB datasets, the proposed method achieved a competitive performance and better anomaly localization.

Source: IEEE Open Journal of Signal Processing

DOI: 10.1109/ojsp.2025.3580967

Authors: An D. Le, Shiwei Jin, Sungbal Seo, You-Suk Bae, Truong Q. Nguyen

Institutions: University of California San Diego, Tech University of Korea

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,795

Funder: Institute for Information and Communications Technology Promotion