Early-Exit Deep Neural Network - A Comprehensive Survey
ACM Computing Surveys · 31.03.2025 · 57 (3) · 1-37
DOI: 10.1145/3698767 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 22.11.2024. Verfasst von Haseena Rahmath P und 4 weiteren Autor:innen. Die Arbeit wurde bisher 101-mal zitiert (Crossref) und nennt 159 Literaturangaben.
Abstract (Originalsprache)
Deep neural networks (DNNs) typically have a single exit point that makes predictions by running the entire stack of neural layers. Since not all inputs require the same amount of computation to reach a confident prediction, recent research has focused on incorporating multiple “exits” into the conventional DNN architecture. Early-exit DNNs are multi-exit neural networks that attach many side branches to the conventional DNN, enabling inference to stop early at intermediate points. This approach offers several advantages, including speeding up the inference process, mitigating the vanishing gradients problems, reducing overfitting and overthinking tendencies. It also supports DNN partitioning across devices and is ideal for multi-tier computation platforms such as edge computing. This article decomposes the early-exit DNN architecture and reviews the recent advances in the field. The study explores its benefits, designs, training strategies, and adaptive inference mechanisms. Various design challenges, application scenarios, and future directions are also extensively discussed.
Zitieren
APA
P, H. R., Srivastava, V., Chaurasia, K., Pacheco, R. G., & Couto, R. S. (2025). Early-Exit Deep Neural Network - A Comprehensive Survey. ACM Computing Surveys, 57(3), 1-37. https://doi.org/10.1145/3698767
Vancouver
P HR, Srivastava V, Chaurasia K, Pacheco RG, Couto RS. Early-Exit Deep Neural Network - A Comprehensive Survey. ACM Computing Surveys. 2025;57(3):1-37. doi:10.1145/3698767
BibTeX
@article{P2025,
author = {P, Haseena Rahmath and Srivastava, Vishal and Chaurasia, Kuldeep and Pacheco, Roberto G. and Couto, Rodrigo S.},
title = {Early-Exit Deep Neural Network - A Comprehensive Survey},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {3},
pages = {1--37},
doi = {10.1145/3698767}
}
EUVIMED