SOURCE-LINKED INTELLIGENCE

Layerwise Tunable Lifting Scheme for the Convolutional Neural Network

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global