Energy-efficient amortized inference with cascaded deep classifiers

Jiaqi Guan, Yang Liu, Qiang Liu, Jian Peng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that optimizes the prediction accuracy and energy cost simultaneously, thus enabling effective cost-accuracy trade-off at test time. In our framework, each data instance is pushed into a cascade of deep neural networks with increasing sizes, and a selection module is used to sequentially determine when a sufficiently accurate classifier can be used for this data instance. The cascade of neural networks and the selection module are jointly trained in an end-to-end fashion by the REINFORCE algorithm to optimize a trade-off between the computational cost and the predictive accuracy. Our method is able to simultaneously improve the accuracy and efficiency by learning to assign easy instances to fast yet sufficiently accurate classifiers to save computation and energy cost, while assigning harder instances to deeper and more powerful classifiers to ensure satisfiable accuracy. Moreover, we demonstrate our method's effectiveness with extensive experiments on CIFAR-10/100, ImageNet32x32 and original ImageNet dataset.

Original languageEnglish (US)
Title of host publicationProceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
EditorsJerome Lang
PublisherInternational Joint Conferences on Artificial Intelligence
Pages2184-2190
Number of pages7
ISBN (Electronic)9780999241127
DOIs
StatePublished - 2018
Event27th International Joint Conference on Artificial Intelligence, IJCAI 2018 - Stockholm, Sweden
Duration: Jul 13 2018Jul 19 2018

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2018-July
ISSN (Print)1045-0823

Other

Other27th International Joint Conference on Artificial Intelligence, IJCAI 2018
CountrySweden
CityStockholm
Period7/13/187/19/18

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Energy-efficient amortized inference with cascaded deep classifiers'. Together they form a unique fingerprint.

  • Cite this

    Guan, J., Liu, Y., Liu, Q., & Peng, J. (2018). Energy-efficient amortized inference with cascaded deep classifiers. In J. Lang (Ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 (pp. 2184-2190). (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2018-July). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2018/302