TY - GEN
T1 - Energy-efficient amortized inference with cascaded deep classifiers
AU - Guan, Jiaqi
AU - Liu, Yang
AU - Liu, Qiang
AU - Peng, Jian
N1 - Publisher Copyright:
© 2018 International Joint Conferences on Artificial Intelligence. All right reserved.
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85055705353&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85055705353&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2018/302
DO - 10.24963/ijcai.2018/302
M3 - Conference contribution
AN - SCOPUS:85055705353
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 2184
EP - 2190
BT - Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
A2 - Lang, Jerome
PB - International Joint Conferences on Artificial Intelligence
T2 - 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
Y2 - 13 July 2018 through 19 July 2018
ER -