Ordinal Regression with Multiple Output CNN for Age Estimation

By Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua. Computer Vision and Pattern Recognition, 2016

696 citations recorded by the source corpus.

To address the non-stationary property of aging patterns, age estimation can be cast as an ordinal regression problem. However, the processes of extracting features and learning a regression model are often separated and optimized independently in previous work. In this paper, we propose an End-to-End learning approach to address ordinal regression problems using deep Convolutional Neural Network, which could simultaneously conduct feature learning and regression modeling. In particular, an ordinal regression problem is transformed into a series of binary classification sub-problems. And we propose a multiple output CNN learning algorithm to collectively solve these classification sub-problems, so that the correlation between these tasks could be explored. In addition, we publish an Asian Face Age Dataset (AFAD) containing more than 160K facial images with precise age ground-truths, which is the largest public age dataset to date. To the best of our knowledge, this is the first work to address ordinal regression problems by using CNN, and achieves the state-of-the-art performance on both the MORPH and AFAD datasets.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6618cff7f2ed440a0d2fa9e74ad5469df5cdbe4c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Improving Smiling Detection with Race and Gender Diversity (2017, background): “The closely related task of face attribute detection has seen similar gains, with work on everything from age estimation [25] to arched eyebrow detection [22] demonstrating significant strides in what modern machine learning can do.”
InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity (2017, methodology): “Detecting and recognizing different face attributes has become an increasingly feasible machine learning task due to the rise in deep learning techniques and large people-focused datasets (Niu et al., 2016; Liu et al., 2015).”
Rank consistent ordinal regression for neural networks with application to age estimation (2019, methodology): “However, neural network-based implementations of this approach commonly suffer from classifier inconsistencies among the binary rankings (Niu et al., 2016).”
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation (2020, result): “Similar to our observation, the research community in computer vision has long observed that both vanilla classification and regression formulation has drawbacks in age estimation (Rothe et al., 2015; Niu et al., 2016; Zhang et al., 2017).”
Deep Ordinal Regression Network for Monocular Depth Estimation (2018, methodology): “In computer vision, ordinal regression has been combined with DCNNs to address the age estimation problem [44].”
Incorporating Side Information by Adaptive Convolution (2017, methodology): “…task is used as our auxiliary task because, empirically, classiﬁcation is more robust to train than regression since it only needs to decide to which class the input belongs (i.e., form partitions of the feature space), rather than predicts an exact real number (Niu et al. 2016; Rothe et al. 2015).”