.png){kind=icon}
.png){kind=icon}
Return
Surrogate network-based sparseness hyper-parameter optimization for deep expression recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2020.107701.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
For facial expression recognition, the sparseness constraints of the features or weights can improve the generalization ability of a deep network. However, the optimization of the hyper-parameters in fusing different sparseness strategies demands much computation, when the traditional gradient-based algorithms are used. In this work, an iterative framework with surrogate network is proposed for the optimization of hyper-parameters in fusing different sparseness strategies. In each iteration, a network with significantly smaller model complexity is fitted to the original large network based on four Euclidean losses, where the hyper-parameters are optimized with heuristic optimizers. Since the surrogate network uses the same deep metrics and embeds the same hyper-parameters as the original network, the optimized hyper-parameters are then used for the training of the original deep network in the next iteration. While the performance of the proposed algorithm is justified with a tiny model, i.e. LeNet on the FER2013 database, our approach achieved competitive performances on six publicly available expression datasets, i.e., FER2013, CK+, Oulu-CASIA, MMI, AFEW and AffectNet. (C) 2020 Elsevier Ltd. All rights reserved.
Keywords:
Expression recognition
Deep sparseness strategies
Hyper-parameter optimization
Surrogate network
Heuristic optimizer
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
View more organizations