# Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems

Source: [Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems](<https://www.sota2.com/research/paper/68fa7a2e1e209131cea819b1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:14:13.950Z

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

Published: 2025-07-21T23:57:03.000Z

## Abstract

This work introduces a stop-band energy constraint for filters in orthogonal tunable wavelet units with a lattice structure, aimed at improving image classification and anomaly detection in CNNs, especially on texture-rich datasets. Integrated into ResNet-18, the method enhances convolution, pooling, and downsampling operations, yielding accuracy gains of 2.48% on CIFAR-10 and 13.56% on the Describable Textures dataset. Similar improvements are observed in ResNet-34. On the MVTec hazelnut anomaly detection task, the proposed method achieves competitive results in both segmentation and detection, outperforming existing approaches.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.16114>)

[PDF](<https://arxiv.org/pdf/2507.16114.pdf>)