中文标题#
卷积神经网络在计算机视觉问题中正交可调小波单元的阻带能量约束
英文标题#
Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems
中文摘要#
这项工作为正交可调小波单元中具有格子结构的滤波器引入了阻带能量约束，旨在提高卷积神经网络中的图像分类和异常检测性能，尤其是在纹理丰富的数据集上。 集成到 ResNet-18 中，该方法增强了卷积、池化和下采样操作，在 CIFAR-10 上的准确率提升了 2.48%，在可描述纹理数据集上的准确率提升了 13.56%。 ResNet-34 中也观察到了类似的改进。 在 MVTec 榛子异常检测任务中，所提出的方法在分割和检测方面都取得了具有竞争力的结果，优于现有方法。
英文摘要#
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.
PDF 获取#
抖音扫码查看更多精彩内容