Learning Accurate Performance Predictors for Ultrafast Automated Model Compression

In this paper, we propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Conventional non-differen-tiable methods discretely search the desirable compression policy based on the accuracy from exhaustively trained lightweight models, and existing di...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	International journal of computer vision Ročník 131; číslo 7; s. 1761 - 1783
Hlavní autoři:	Wang, Ziwei, Lu, Jiwen, Xiao, Han, Liu, Shengyu, Zhou, Jie
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York Springer US 01.07.2023 Springer Springer Nature B.V
Témata:	Accuracy Artificial Intelligence Automation Complexity Computational efficiency Computer Imaging Computer Science Computing costs Image classification Image compression Image Processing and Computer Vision Object recognition Optimization Pattern Recognition Pattern Recognition and Graphics Performance prediction Searching Vision Compression policy optimization Performance predictor Evolutionary search Uncertainty estimation Automated model compression
ISSN:	0920-5691, 1573-1405
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!