Ordinal Regression with Multiple Output CNN for Age Estimation

Niu, Zhenxing; Zhou, Mo; Wang, Le; Gao, Xinbo; Hua, Gang

doi:10.1109/cvpr.2016.532

Cited by 501 publications

(448 citation statements)

References 19 publications

Supporting

Mentioning

422

Contrasting

Unclassified

Order By: Relevance

“…Based on recent work by Niu et al [22], we now formulate an ordinal output layer that maps the multi-class problem to have multiple outputs. In the case of positive valence, the problem is transformed from four to only three output units denoted by t 1 , t 2 , and t 3 .…”

Section: Methods: Ordinal Convolutional Neural Network With Wide mentioning

confidence: 99%

See 1 more Smart Citation

Ordinal convolutional neural networks for predicting RDoC positive valence psychiatric symptom severity scores

Rios¹,

Kavuluru²

2017

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Background The CEGS N-GRID 2016 Shared Task in Clinical Natural Language Processing (NLP) provided a set of 1000 neuropsychiatric notes to participants as part of a competition to predict psychiatric symptom severity scores. This paper summarizes our methods, results, and experiences based on our participation in the second track of the shared task. Objective Classical methods of text classification usually fall into one of three problem types: binary, multi-class, and multi-label classification. In this effort, we study ordinal regression problems with text data where misclassifications are penalized differently based on how far apart the ground truth and model predictions are on the ordinal scale. Specifically, we present our entries (methods and results) in the N-GRID shared task in predicting research domain criteria (RDoC) positive valence ordinal symptom severity scores (absent, mild, moderate, and severe) from psychiatric notes. Methods We propose a novel convolutional neural network (CNN) model designed to handle ordinal regression tasks on psychiatric notes. Broadly speaking, our model combines an ordinal loss function, a CNN, and conventional feature engineering (wide features) into a single model which is learned end-to-end. Given interpretability is an important concern with nonlinear models, we apply a recent approach called locally interpretable model-agnostic explanation (LIME) to identify important words that lead to instance specific predictions. Results Our best model entered into the shared task placed third among 24 teams and scored a macro mean absolute error (MMAE) based normalized score (100 · (1 − M M AE)) of 83.86. Since the competition, we improved our score (using basic ensembling) to 85.55, comparable with the winning shared task entry. Applying LIME to model predictions, we demonstrate the feasibility of instance specific prediction interpretation by identifying words that led to a particular decision. Conclusion In this paper, we present a method that successfully uses wide features and an ordinal loss function applied to convolutional neural networks for ordinal text classification specifically in predicting psychiatric symptom severity scores. Our approach leads to excellent performance on the N-GRID shared task and is also amenable to interpretability using existing model-agnostic approaches.

show abstract

Section: Methods: Ordinal Convolutional Neural Network With Wide mentioning

confidence: 99%

“…In this work, we expand on recent work for estimating age in images [22]. Specifically, we adapt their multiple output ordinal regression layer to CNNs more appropriate for text.…”

Section: Related Workmentioning

confidence: 99%

Ordinal convolutional neural networks for predicting RDoC positive valence psychiatric symptom severity scores

Rios¹,

Kavuluru²

2017

Journal of Biomedical Informatics

View full text Add to dashboard Cite

show abstract

“…CNN have been used in different recent studies on age estimation and have demonstrated superior performance compared to other methods. Niu et al [208] used ordinal regression and multiple output CNN for age estimation and reported a MAE of 3.27 on MORPH II and a private Asian Face Age Dataset (AFAD). Chen et al [209] presented a cascaded CNN that had 0.297 Gaussian error on age estimation.…”

Section: Age Estimationmentioning

confidence: 99%

Age estimation via face images: a survey

Angulu

Tapamo

Adewumi

2018

J Image Video Proc.

124

View full text Add to dashboard Cite

Facial aging adversely impacts performance of face recognition and face verification and authentication using facial features. This stochastic personalized inevitable process poses dynamic theoretical and practical challenge to the computer vision and pattern recognition community. Age estimation is labeling a face image with exact real age or age group. How do humans recognize faces across ages? Do they learn the pattern or use age-invariant features? What are these age-invariant features that uniquely identify one across ages? These questions and others have attracted significant interest in the computer vision and pattern recognition research community. In this paper, we present a thorough analysis of recent research in aging and age estimation. We discuss popular algorithms used in age estimation, existing models, and how they compare with each other; we compare performance of various systems and how they are evaluated, age estimation challenges, and insights for future research.

show abstract

“…Such concatenated features are used for the input of the fully connected layer, and the output is used for the final age feature. Second, we compared some studies on a typical method, such as [13] and [31]. They transformed the traditional regression problem into a binary classification problem or ordinal problem.…”

Section: Age Estimation In Morph-iimentioning

confidence: 99%

Robust Deep Age Estimation Method Using Artificially Generated Image Set

Jang¹,

Jeon²,

Kim³

et al. 2017

ETRI Journal

View full text Add to dashboard Cite

Human age estimation is one of the key factors in the field of Human-Robot Interaction/Human-Computer Interaction (HRI/HCI). Owing to the development of deep-learning technologies, age recognition has recently been attempted. In general, however, deep learning techniques require a large-scale database, and for age learning with variations, a conventional database is insufficient. For this reason, we propose an age estimation method using artificially generated data. Image data are artificially generated through 3D information, thus solving the problem of shortage of training data, and helping with the training of the deep-learning technique. Augmentation using 3D has advantages over 2D because it creates new images with more information. We use a deep architecture as a pre-trained model, and improve the estimation capacity using artificially augmented training images. The deep architecture can outperform traditional estimation methods, and the improved method showed increased reliability. We have achieved state-of-the-art performance using the proposed method in the Morph-II dataset and have proven that the proposed method can be used effectively using the Adience dataset.

show abstract

Ordinal Regression with Multiple Output CNN for Age Estimation

Cited by 501 publications

References 19 publications

Ordinal convolutional neural networks for predicting RDoC positive valence psychiatric symptom severity scores

Ordinal convolutional neural networks for predicting RDoC positive valence psychiatric symptom severity scores

Age estimation via face images: a survey

Robust Deep Age Estimation Method Using Artificially Generated Image Set

Contact Info

Product

Resources

About