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

arXiv: https://arxiv.org/abs/2507.16114 · HTML: https://mlsanity.com/paper/2507.16114/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows](https://mlsanity.com/paper/2107.12571/) (2021)
- [Spectral Representations for Convolutional Neural Networks](https://mlsanity.com/paper/1506.03767/) (2015)
- [Wavelet Integrated CNNs for Noise-Robust Image Classification](https://mlsanity.com/paper/2005.03337/) (2020)
- [Learning strides in convolutional neural networks](https://mlsanity.com/paper/2202.01653/) (2022)
- [Wavelet-Attention CNN for Image Classification](https://mlsanity.com/paper/2201.09271/) (2022)
- [AlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platform](https://mlsanity.com/paper/2112.13341/) (2021)
- [A PM2.5 concentration prediction framework with vehicle tracking system: From cause to effect](https://mlsanity.com/paper/2212.01761/) (2022)

## Built on by (most cited first, 1 of 1)

- [Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation](https://mlsanity.com/paper/2602.14199/) (2026)

## Abstract (arXiv)

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.