New Coarse-to-Fine Approaches for Age Estimation Based on Separable Convolutions
Open Access
- 16 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 130306-130318
Abstract
In this paper, we study lightweight age estimation methods based on a coarse-to-fine approach in which the network performs age prediction with multiple stages. In each stage, the network only focuses on refining the coarse age prediction generated from the previous stage. The final age prediction is the combination of all staged prediction values. We observe that these stages have a causal relationship, that is, the output of each stage is highly correlated with outputs of its former stages. Thus, each stage should share the information of its previous stage before making a refined prediction. Based on this observation, we construct a new compact CNN model called Homologous Stagewise Regression Network (HSR-Net). In HSR-Net, each stage shares the information of the last convolutional layer and then generates its own refined value. In addition, HSR-Net also addresses the age group ambiguity problem by utilizing an easy dynamic range construction. In order to enhance the prediction performance of HSR-Nets, it is naive to increase the number of kernels in each convolutional layer of HSR-Nets. However, the constructed HSR-Net has extremely large parameter size. To address this problem, we propose the separable HSR-Nets (SepHSR-Nets) where standard convolutions are replaced by depth-wise separable convolutions in the convolutional layers of HSR-Nets. In general, the parameter size of SepHSR-Nets ranges from 10K to 75K without sacrificing prediction performance. Experimental results show that SepHSR-Nets achieve competitive performance compared with the state-of-the-art compact models. Our code, data, and models are available at https://github.com/yanjenhuang/hsr-net.Keywords
Funding Information
- National Science and Technology Council, Taiwan (NSTC-110-2221-E-305-006-MY2)
- National Taipei University of Technology (110-NTPU-ORDA-F-004, 2023-NTPU-ORD-01)
This publication has 41 references indexed in Scilit:
- Deep Expectation of Real and Apparent Age from a Single Image Without Facial LandmarksInternational Journal of Computer Vision, 2016
- Some Like It Hot — Visual Guidance for Preference Prediction2016
- Rethinking the Inception Architecture for Computer Vision2016
- Ordinal Regression with Multiple Output CNN for Age Estimation2016
- DEX: Deep EXpectation of Apparent Age from a Single Image2015
- Going deeper with convolutions2015
- Age Estimation by Multi-scale Convolutional Network2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Human Age Estimation and Sex Classification2012
- MORPH: A Longitudinal Image Database of Normal Adult Age-Progression2006