为卷积网络中的可调小波单元添加阻带能量约束，提升纹理图像分类与异常检测性能。
Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems
- 在正交可调小波单元中引入阻带能量约束，优化滤波器设计。
- 在CIFAR-10上提升2.48%，在纹理数据集上提升13.56%。
- 适合处理纹理丰富图像的任务，如异常检测与分类。
本文提出一种针对具有格结构的正交可调小波单元滤波器的阻带能量约束方法，旨在提升卷积神经网络在图像分类和异常检测任务中的表现，尤其在纹理丰富的数据集上。该方法集成于ResNet-18，增强了卷积、池化与下采样操作，在CIFAR-10上实现2.48%的准确率提升，在可描述纹理数据集上提升13.56%。类似效果也在ResNet-34上观察到。在MVTec榛子异常检测任务中，该方法在分割与检测方面均达到竞争性结果，优于现有方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。