Early-Exit with Class Exclusion for Efficient Inference of Neural Networks

arXiv:2309.13443v2 Announce Type: replace
Abstract: Deep neural networks (DNNs) have been successfully applied in various fields. In DNNs, a large number of multiply-accumulate (MAC) operations are required to be performed, posing critical challenges in applying them in resource-constrained platforms, e.g., edge devices. To address this challenge, in this paper, we propose a class-based early-exit for dynamic inference. Instead of pushing DNNs to make a dynamic decision at intermediate layers, we take advantage of the learned features in these layers to …

arxiv class cs.lg exit inference networks neural networks type