pith. sign in

arxiv: 2104.10461 · v2 · pith:3GYVATVInew · submitted 2021-04-21 · 💻 cs.LG · cs.CV

Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning

classification 💻 cs.LG cs.CV
keywords learningmulti-exitaccuracyarchitecturescurriculumearlytrainingcost
0
0 comments X
read the original abstract

Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time. Multi-exit architectures allow deep neural networks to terminate their execution early in order to adhere to tight deadlines at the cost of accuracy. To mitigate this cost, in this paper we introduce a novel method called Multi-Exit Curriculum Learning that utilizes curriculum learning, a training strategy for neural networks that imitates human learning by sorting the training samples based on their difficulty and gradually introducing them to the network. Experiments on CIFAR-10 and CIFAR-100 datasets and various configurations of multi-exit architectures show that our method consistently improves the accuracy of early exits compared to the standard training approach.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.