Hybrid network compression through tensor decompositions and pruning - Laboratoire d'Informatique et Systèmes Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Hybrid network compression through tensor decompositions and pruning

Résumé

The application of network compression methods, combining tensor decompositions and pruning, has demonstrated significant potential in harnessing the benefits of both strategies. This research introduces NORTON (hybrid Network cOmpression thRough Tensor decompOsitions and pruNing), a novel hybrid approach for network compression. The key innovation lies in the introduction of filter decomposition, enhancing the detailed breakdown of the network while preserving the multidimensional properties of filters. Our method incorporates a structured pruning approach, seamlessly integrating the decomposed model. Through a comprehensive set of experiments across various architectures, benchmark datasets, and representative vision tasks, the efficacy of our approach is highlighted.
Fichier principal
Vignette du fichier
_EUSIPCO_2024__Hybrid_network_compression_through_tensor_decompositions_and_pruning.pdf (1.12 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04584032 , version 1 (22-05-2024)

Identifiants

  • HAL Id : hal-04584032 , version 1

Citer

Van Tien Pham, Yassine Zniyed, Thanh Phuong Nguyen. Hybrid network compression through tensor decompositions and pruning. 32nd European Signal Processing Conference, EUSIPCO 2024, Aug 2024, Lyon, France. ⟨hal-04584032⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More