发表机构
University of California San Diego; Tech University of Korea（加州大学圣迭戈分校; 韩国科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一族基于格结构的可调提升方案，用于双正交小波滤波器组，集成到ResNet-18中在图像分类和异常检测任务上均取得性能提升。
AI 中文摘要
本文提出了一族用于双正交小波滤波器组的可调提升方案。我们提出了三种提升策略：低通调谐（LS-LayLatt-LP）、高通调谐（LS-LayLatt-HP）以及一种顺序提升方案，该方案联合自适应低频和高频分支（LS-LayLatt-Sequential）。所有提出的设计均采用基于格结构的提升结构进行表述，该结构保证了提升函数内任意参数值的可逆性和稳定性。我们通过将所提方法集成到ResNet-18骨干网络中，在可描述纹理数据集（DTD）上进行图像分类，以及在MVTec-AD数据集和私有KRC102S数据集上的榛子图像上进行异常检测，对所提方法进行了评估。实验结果表明，在所有评估任务中均取得了一致的性能提升。
英文摘要
This work introduces a family of tunable lifting schemes for biorthogonal wavelet filter banks. We propose three lifting strategies: low-pass tuning (LS-LayLatt-LP), high-pass tuning (LS-LayLatt-HP), and a sequential lifting scheme that jointly adapts low- and high-frequency branches (LS-LayLatt-Sequential). All proposed designs are formulated using a lattice-based lifting structure, which guarantees invertibility and stability for arbitrary parameter values within the lifting functions. We evaluated the proposed methods by integrating them into a ResNet-18 backbone for image classification on the Describable Textures Dataset (DTD), as well as for anomaly detection on hazelnut images from the MVTec-AD dataset and private KRC102S dataset. Experimental results demonstrate consistent performance improvements across all evaluated tasks.
