Open AccessProceedings Article10.1109/ICIP.2018.8451606

Fusion Network for Face-Based Age Estimation

- 04 Oct 2018

- pp 2675-2679

TL;DR: A novel CNN architecture called Fusion Network (Fusion-Net) is proposed to tackle the age estimation problem and it is shown that the FusionNet significantly outperforms other state-of-the-art models on the MORPH II benchmark.

Abstract: Convolutional Neural Networks (CNN) have been applied to age-related research as the core framework Although faces are composed of numerous facial attributes, most works with CNNs still consider a face as a typical object and do not pay enough attention to facial regions that carry age-specific feature for this particular task In this paper, we propose a novel CNN architecture called Fusion Network (Fusion-Net) to tackle the age estimation problem Apart from the whole face image, the FusionNet successively takes several age-specific facial patches as part of the input to emphasize the age-specific features Through experiments, we show that the FusionNet significantly outperforms other state-of-the-art models on the MORPH II benchmark

AI Agents for this Paper

Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps

Most frequently asked questions

1. What contributions have the authors mentioned in the paper "Fusion network for face-based age estimation" ?

In this paper, the authors propose a novel CNN architecture called Fusion Network ( FusionNet ) to tackle the age estimation problem.. Through experiments, the authors show that the FusionNet significantly outperforms other state-of-the-art models on the MORPH II benchmark.

Table 2. MAE values of three state-of-the-art CNN-based models and our method on MORPH II dataset. The best result is highlighted in bold.

Table 1. Comparison between our proposed network and a baseline model. The best result is highlighted in bold.

Fig. 1. Data feeding sequence in the FusionNet. The model takes the original face and a total of n facial patches as inputs.

Fig. 2. The architecture of the Fusion Network for face-based age estimation. The selected patches are fed to the network sequentially as the secondary learning source. The input of patches can be viewed as shortcut connections to enhance the learning of age-specific feature. We use five patches (P1 to P5) to keep the balance between the training efficiency and the performance. The final output is produced by a single fully-connected (FC) layer.

Citations

•Journal Article•10.1109/TIP.2021.3084106

Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss

Haoyi Wang, +2 more

- 01 Jul 2020

- arXiv: Computer Vision and Pattern Recog...

TL;DR: To achieve high synthesis accuracy, the proposed method tackles the mode collapse issue with a novel Conditional Discriminator Pool, which consists of multiple discriminators, each targeting one particular age category, and uses a novel Adversarial Triplet loss.

...read moreread less

•Journal Article•10.18421/tem121-61

Predicting Age and Gender Using AlexNet

Q. K. Abood, +1 more

- 27 Feb 2023

- TEM Journal

TL;DR: In this article , AlexNet achieves a 98% accuracy rate across its lifespan of system results and the UTKFace dataset is used as the backbone of the face estimating system, which provides the foundation of this function.

...read moreread less

Book Chapter•10.1007/978-3-030-20482-2_20

Real-Time Age Detection Using a Convolutional Neural Network

Siphesihle Philezwini Sithungu, +1 more

- 26 Jun 2019

TL;DR: This paper presents a solution that makes use of a lightweight Convolutional Neural Network model, built according to a modification of the LeNet-5 architecture to perform age detection, for both males and females, in real-time.

...read moreread less

Book Chapter•10.1007/978-3-030-32583-1_1

Using Age Information as a Soft Biometric Trait for Face Image Analysis

Haoyi Wang, +3 more

- 01 Jan 2020

TL;DR: This chapter introduces the concepts and theory behind the three main areas of age-related face image analysis and how they can be used in practical biometric applications, and analyses the difficulties involved in these applications.

...read moreread less

Journal Article•10.3390/data8100145

Attention-Based Human Age Estimation from Face Images to Enhance Public Security

Md. Ashiqur Rahman, +3 more

- 25 Sep 2023

TL;DR: Experimental results on different aging face databases show the remarkable advantages of the proposed attention-based CNN model over the conventional CNN model by attaining the lowest mean absolute error and the lowest number of parameters with a better cumulative score.

...read moreread less

References

•Proceedings Article•10.1109/CVPR.2016.90

Deep Residual Learning for Image Recognition

Kaiming He, +3 more

- 27 Jun 2016

TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.

...read moreread less

198.7K

•Posted Content

Deep Residual Learning for Image Recognition

Kaiming He, +3 more

- 10 Dec 2015

- arXiv: Computer Vision and Pattern Recog...

TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

...read moreread less

117.9K

•Proceedings Article

Very Deep Convolutional Networks for Large-Scale Image Recognition

Karen Simonyan, +1 more

- 04 Sep 2014

TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

...read moreread less

102.6K

•Journal Article•10.1145/3065386

ImageNet classification with deep convolutional neural networks

Alex Krizhevsky, +2 more

- 24 May 2017

- Communications of The ACM

TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

...read moreread less

98.2K

•Proceedings Article

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky, +2 more

- 03 Dec 2012

TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.

...read moreread less

88.4K

...

Expand

Fusion Network for Face-Based Age Estimation

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What contributions have the authors mentioned in the paper "Fusion network for face-based age estimation" ?

Figures

Citations

Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss

Predicting Age and Gender Using AlexNet

Real-Time Age Detection Using a Convolutional Neural Network

Using Age Information as a Soft Biometric Trait for Face Image Analysis

Attention-Based Human Age Estimation from Face Images to Enhance Public Security

References

Deep Residual Learning for Image Recognition

Deep Residual Learning for Image Recognition

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet classification with deep convolutional neural networks

ImageNet Classification with Deep Convolutional Neural Networks

Related Papers (5)

Biased face patching approach for age invariant face recognition using convolutional neural network

Age and gender classification using convolutional neural networks

On the use of DAG-CNN architecture for age estimation with multi-stage features fusion

An All-In-One Convolutional Neural Network for Face Analysis

Facial Expression Recognition by Multi-Scale CNN with Regularized Center Loss