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

• URL: http://arxiv.org/abs/2507.16114v1
• Date: Mon, 21 Jul 2025 23:57:03 GMT
• Title: Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems
• Authors: An D. Le, Hung Nguyen, Sungbal Seo, You-Suk Bae, Truong Q. Nguyen,
• Abstract summary: This work introduces a stop-band energy constraint for filters in tunable wavelet units with a lattice structure, aimed at improving image classification and anomaly detection in CNNs.<n> 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.<n>On the MVTec hazelnut anomaly detection task, the proposed method achieves competitive results in both segmentation and detection, outperforming existing approaches.
• Score: 8.116961165681603
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Spectral Feature Extraction for Robust Network Intrusion Detection Using MFCCs [0.4779196219827506]
  We propose a novel approach for identifying anomalies in IoT network traffic by leveraging the Mel-frequency cepstral coefficients (MFCC) and ResNet-18.<n>Our approach combines the strengths of MFCCs with the robust feature extraction capabilities of ResNet-18, offering a powerful framework for anomaly detection.
  arXiv  Detail & Related papers  (2025-07-14T01:25:26Z)
• SDTN and TRN: Adaptive Spectral-Spatial Feature Extraction for Hyperspectral Image Classification [1.2871580250533408]
  Hyperspectral image classification plays a pivotal role in precision agriculture, providing accurate insights into crop health monitoring, disease detection, and soil analysis.<n>Traditional methods struggle with high-dimensional data, spectral-spatial redundancy, and the scarcity of labeled samples, often leading to suboptimal performance.<n>To address these challenges, we propose the Self-Adaptive- Regularized Network (SDTN), which combines tensor decomposition with regularization mechanisms to dynamically adjust tensor ranks.<n>This approach not only maintains high classification accuracy but also significantly reduces computational complexity, making the framework highly suitable for real-time deployment in resource-constrained environments.
  arXiv  Detail & Related papers  (2025-07-13T04:53:33Z)
• Biorthogonal Tunable Wavelet Unit with Lifting Scheme in Convolutional Neural Network [2.9377547378375803]
  The proposed unit enhances convolution, pooling, and downsampling operations, leading to improved image classification and anomaly detection in convolutional neural networks (CNN)<n>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%.<n>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.
  arXiv  Detail & Related papers  (2025-07-01T13:42:46Z)
• EECD-Net: Energy-Efficient Crack Detection with Spiking Neural Networks and Gated Attention [6.723950151272841]
  This paper proposes a multi-stage detection approach for road crack detection, EECD-Net, to enhance accuracy and energy efficiency of instrumentation.<n>Super-Resolution Convolutional Neural Network (SRCNN) is employed to address the inherent challenges of low-quality images.<n>A Spike Convolution Unit (SCU) with Continuous Integrate-and-Fire (CIF) neurons is proposed to convert these images into sparse pulse sequences.<n>Experiments on the CrackVision12K benchmark demonstrate that EECD-Net achieves a remarkable 98.6% detection accuracy.
  arXiv  Detail & Related papers  (2025-06-05T00:19:36Z)
• Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks [58.050130177241186]
  Noise perturbations often corrupt 3-D point clouds, hindering downstream tasks such as surface reconstruction, rendering, and further processing. This paper introduces finegranularity dynamic graph convolutional networks called GDGCN, a novel approach to denoising in 3-D point clouds.
  arXiv  Detail & Related papers  (2024-11-21T14:19:32Z)
• Dual-Frequency Filtering Self-aware Graph Neural Networks for Homophilic and Heterophilic Graphs [60.82508765185161]
  We propose Dual-Frequency Filtering Self-aware Graph Neural Networks (DFGNN) DFGNN integrates low-pass and high-pass filters to extract smooth and detailed topological features. It dynamically adjusts filtering ratios to accommodate both homophilic and heterophilic graphs.
  arXiv  Detail & Related papers  (2024-11-18T04:57:05Z)
• Wavelet-based Bi-dimensional Aggregation Network for SAR Image Change Detection [53.842568573251214]
  Experimental results on three SAR datasets demonstrate that our WBANet significantly outperforms contemporary state-of-the-art methods. Our WBANet achieves 98.33%, 96.65%, and 96.62% of percentage of correct classification (PCC) on the respective datasets.
  arXiv  Detail & Related papers  (2024-07-18T04:36:10Z)
• DCNN: Dual Cross-current Neural Networks Realized Using An Interactive Deep Learning Discriminator for Fine-grained Objects [48.65846477275723]
  This study proposes novel dual-current neural networks (DCNN) to improve the accuracy of fine-grained image classification. The main novel design features for constructing a weakly supervised learning backbone model DCNN include (a) extracting heterogeneous data, (b) keeping the feature map resolution unchanged, (c) expanding the receptive field, and (d) fusing global representations and local features.
  arXiv  Detail & Related papers  (2024-05-07T07:51:28Z)
• ASWT-SGNN: Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network [20.924559944655392]
  This paper proposes an Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network (ASWT-SGNN) ASWT-SGNN accurately approximates the filter function in high-density spectral regions, avoiding costly eigen-decomposition. It achieves comparable performance to state-of-the-art models in node classification tasks.
  arXiv  Detail & Related papers  (2023-12-10T03:07:42Z)
• From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks [82.21746840893658]
  This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network. We show that while the ResNet-18 model trained on DWT spectrograms achieves a high recognition accuracy, attacking this model is relatively more costly for the adversary.
  arXiv  Detail & Related papers  (2022-04-14T15:14:08Z)
• CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds [51.47100091540298]
  We present Cascaded Primitive Fitting Networks (CPFN) that relies on an adaptive patch sampling network to assemble detection results of global and local primitive detection networks. CPFN improves the state-of-the-art SPFN performance by 13-14% on high-resolution point cloud datasets and specifically improves the detection of fine-scale primitives by 20-22%.
  arXiv  Detail & Related papers  (2021-08-31T23:27:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.