|国家预印本平台
首页|Biorthogonal Tunable Wavelet Unit with Lifting Scheme in Convolutional Neural Network

Biorthogonal Tunable Wavelet Unit with Lifting Scheme in Convolutional Neural Network

Biorthogonal Tunable Wavelet Unit with Lifting Scheme in Convolutional Neural Network

来源:Arxiv_logoArxiv
英文摘要

This work introduces a novel biorthogonal tunable wavelet unit constructed using a lifting scheme that relaxes both the orthogonality and equal filter length constraints, providing greater flexibility in filter design. The proposed unit enhances convolution, pooling, and downsampling operations, leading to improved image classification and anomaly detection in convolutional neural networks (CNN). When integrated into an 18-layer residual neural network (ResNet-18), the approach improved classification accuracy on CIFAR-10 by 2.12% and on the Describable Textures Dataset (DTD) by 9.73%, demonstrating its effectiveness in capturing fine-grained details. Similar improvements were observed in ResNet-34. For anomaly detection in the hazelnut category of the MVTec Anomaly Detection dataset, the proposed method achieved competitive and wellbalanced performance in both segmentation and detection tasks, outperforming existing approaches in terms of accuracy and robustness.

An Le、Hung Nguyen、Sungbal Seo、You-Suk Bae、Truong Nguyen

计算技术、计算机技术

An Le,Hung Nguyen,Sungbal Seo,You-Suk Bae,Truong Nguyen.Biorthogonal Tunable Wavelet Unit with Lifting Scheme in Convolutional Neural Network[EB/OL].(2025-07-01)[2025-07-16].https://arxiv.org/abs/2507.00739.点此复制

评论