Coarse-to-Fine Pruning of Graph Convolutional Networks for Skeleton-based Recognition

• Main Author: Sahbi, Hichem
• Other Authors: Systèmes Electroniques (SYEL), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)
• Format: Conference Object
• Language: English
• Published: CCSD 2024
• Subjects: Coarse and fine-grained pruning; graph convolutional networks; skeleton-based recognition; [INFO]Computer Science [cs]; Iceland
• Online Access: https://hal.science/hal-04840300; https://hal.science/hal-04840300v1/document; https://hal.science/hal-04840300v1/file/camera.pdf

International audience Magnitude Pruning is a staple lightweight network design method which seeks to remove connections with the smallest magnitude. This process is either achieved in a structured or unstructured manner. While structured pruning allows reaching high efficiency, unstructured one is more flexible and leads to better accuracy, but this is achieved at the expense of low computational performance. In this paper, we devise a novel coarse-to-fine (CTF) method that gathers the advantages of structured and unstructured pruning while discarding their inconveniences to some extent. Our method relies on a novel CTF parametrization that models the mask of each connection as the Hadamard product involving four parametrizations which capture channel-wise, column-wise, rowwise and entry-wise pruning respectively. Hence, fine-grained pruning is enabled only when the coarse-grained one is disabled, and this leads to highly efficient networks while being effective. Extensive experiments conducted on the challenging task of skeleton-based recognition, using the standard SBU and FPHA datasets, show the clear advantage of our CTF approach against different baselines as well as the related work.