SCoTTi: Save Computation at Training Time with an adaptive framework - Equipe Circuits et Systèmes de Communications Access content directly
Conference Papers Year : 2023

SCoTTi: Save Computation at Training Time with an adaptive framework

Abstract

On-device training is an emerging approach in machine learning where models are trained on edge devices, aiming to enhance privacy protection and real-time performance. However, edge devices typically possess restricted computational power and resources, making it challenging to perform computationally intensive model training tasks. Consequently, reducing resource consumption during training has become a pressing concern in this field. To this end, we propose SCoTTi (Save Computation at Training Time), an adaptive framework that addresses the aforementioned challenge. It leverages an optimizable threshold parameter to effectively reduce the number of neuron updates during training which corresponds to a decrease in memory and computation footprint. Our proposed approach demonstrates superior performance compared to the state-of-the-art methods regarding computational resource savings on various commonly employed benchmarks and popular architectures, including ResNets, MobileNet, and Swin-T.
Fichier principal
Vignette du fichier
Li_SCoTTi_Save_Computation_at_Training_Time_with_an_Adaptive_Framework_ICCVW_2023_paper.pdf (1.22 Mo) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-04592480 , version 1 (29-05-2024)

Identifiers

Cite

Ziyu Li, Enzo Tartaglione, Van-Tam Nguyen. SCoTTi: Save Computation at Training Time with an adaptive framework. 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Oct 2023, Paris, France. pp.1435-1444, ⟨10.1109/ICCVW60793.2023.00156⟩. ⟨hal-04592480⟩
13 View
4 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More