TY - GEN
T1 - Regularize, expand and compress
T2 - 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
AU - Zhang, Jie
AU - Zhang, Junting
AU - Ghosh, Shalini
AU - Li, Dawei
AU - Zhu, Jingwen
AU - Zhang, Heming
AU - Wang, Yalin
N1 - Funding Information:
∗We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/3
Y1 - 2020/3
N2 - Continual learning (CL), the problem of lifelong learning where tasks arrive in sequence, has attracted increasing attention in the computer vision community lately. The goal of CL is to learn new tasks while maintaining the performance on the previously learned tasks. There are two major obstacles for CL of deep neural networks: catastrophic forgetting and limited model capacity. Inspired by the recent breakthroughs in automatically learning good neural network architectures, we develop a nonexpansive AutoML framework for CL termed Regularize, Expand and Compress (REC) to solve the above issues. REC is a unified framework with three highlights: 1) a novel regularized weight consolidation (RWC) algorithm to avoid forgetting, where accessing the data seen in the previously learned tasks is not required; 2) an automatic neural architecture search (AutoML) engine to expand the network to increase model capability; 3) smart compression of the expanded model after a new task is learned to improve the model efficiency. The experimental results on four different image recognition datasets demonstrate the superior performance of the proposed REC over other CL algorithms.
AB - Continual learning (CL), the problem of lifelong learning where tasks arrive in sequence, has attracted increasing attention in the computer vision community lately. The goal of CL is to learn new tasks while maintaining the performance on the previously learned tasks. There are two major obstacles for CL of deep neural networks: catastrophic forgetting and limited model capacity. Inspired by the recent breakthroughs in automatically learning good neural network architectures, we develop a nonexpansive AutoML framework for CL termed Regularize, Expand and Compress (REC) to solve the above issues. REC is a unified framework with three highlights: 1) a novel regularized weight consolidation (RWC) algorithm to avoid forgetting, where accessing the data seen in the previously learned tasks is not required; 2) an automatic neural architecture search (AutoML) engine to expand the network to increase model capability; 3) smart compression of the expanded model after a new task is learned to improve the model efficiency. The experimental results on four different image recognition datasets demonstrate the superior performance of the proposed REC over other CL algorithms.
UR - http://www.scopus.com/inward/record.url?scp=85085492350&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085492350&partnerID=8YFLogxK
U2 - 10.1109/WACV45572.2020.9093585
DO - 10.1109/WACV45572.2020.9093585
M3 - Conference contribution
AN - SCOPUS:85085492350
T3 - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
SP - 843
EP - 851
BT - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 1 March 2020 through 5 March 2020
ER -