{"ID":2892495,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16114","arxiv_id":"2507.16114","title":"Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems","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.","short_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 o...","url_abs":"https://arxiv.org/abs/2507.16114","url_pdf":"https://arxiv.org/pdf/2507.16114v1","authors":"[\"An D. Le\",\"Hung Nguyen\",\"Sungbal Seo\",\"You-Suk Bae\",\"Truong Q. Nguyen\"]","published":"2025-07-21T23:57:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"eess.SP\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}