Progressive Compression of ResNet: An 8.33× Reduction With 90.5% Accuracy Retention for Edge Deployment
Deploying deep convolutional neural networks on edge devices remains challenging due to limited on-chip memory capacity, strict power budgets, and the high energy cost of off-chip DRAM access. Standard architectures such as ResNet offer strong accuracy but require tens of millions of parameters, mak...
Zapisane w:
| Główni autorzy: | , , , , , , |
|---|---|
| Format: | Artigo |
| Język: | Inglês |
| Wydane: |
IEEE
2026-01-01
|
| Seria: | IEEE Access |
| Hasła przedmiotowe: | |
| Dostęp online: | https://ieeexplore.ieee.org/document/11479314/ |
| Etykiety: |
Nie ma etykietki, Dołącz pierwszą etykiete!
|
