Filter Pruning and Re-Initialization via Latent Space Clustering

Volume: 8, Pages: 189587 - 189597
Published: Jan 1, 2020
Abstract
Filter pruning is prevalent for pruning-based model compression. Most filter pruning methods have two main issues: 1) the pruned network capability depends on that of source pretrained models, and 2) they do not consider that filter weights follow a normal distribution. To address these issues, we propose a new pruning method employing both weight re-initialization and latent space clustering. For latent space clustering, we define filters and...
Paper Details
Title
Filter Pruning and Re-Initialization via Latent Space Clustering
Published Date
Jan 1, 2020
Volume
8
Pages
189587 - 189597
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.