Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
10 of 24 references.
References · 10
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2013Describing Textures in the Wildcited by 2,125
- 2019Making Convolutional Networks Shift-Invariant Againcited by 391
- 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
- 2015Spectral Representations for Convolutional Neural Networkscited by 81
- 2020Wavelet Integrated CNNs for Noise-Robust Image Classificationcited by 60
- 2022Learning strides in convolutional neural networkscited by 26
- 2022Wavelet-Attention CNN for Image Classificationcited by 8
- 2021AlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platformcited by 3
- 2022A PM2.5 concentration prediction framework with vehicle tracking system: From cause to effectcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.