Deep Conditional Distribution Learning for Age Estimation

Sun, Haomiao; Pan, Hongyu; Han, Hu; Shan, Shiguang

doi:10.1109/tifs.2021.3114066

Cited by 12 publications

(4 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, [2] introduced an age grouping strategy including genders and sub-groups to facilitate the age estimation task. [3] proposed a deep conditional distribution learning which is conditioned to several attributes such as gender and age.…”

Section: Age Estimationmentioning

confidence: 99%

“…Variance in Appearance People of the same age have remarkable variance in their appearance [2], which makes the age estimation challenging. To resolve this issue, some researchers have suggested age, gender and racial grouping [2,3]. Nevertheless, such approaches fail when the grouping strategy is erroneous or when the same age groups are highly varying.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TAA-GCN: A temporally aware Adaptive Graph Convolutional Network for age estimation

Korban

Youngs²,

Acton³

2023

Pattern Recognition

View full text Add to dashboard Cite

Section: Age Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

TAA-GCN: A temporally aware Adaptive Graph Convolutional Network for age estimation

Korban

Youngs²,

Acton³

2023

Pattern Recognition

View full text Add to dashboard Cite

“…Sun et al. [19] introduced a novel deep conditional distribution learning (DCDL) method, which could flexibly leverage a varying number of auxiliary face attributes to achieve adaptive age‐related feature learning.…”

Section: Related Workmentioning

confidence: 99%

Multi‐task multi‐scale attention learning‐based facial age estimation

Shi

Zhao

Zhang

et al. 2023

IET Signal Processing

View full text Add to dashboard Cite

Face‐based age estimation strongly depends on deep residual networks (ResNets), used as the backbone in the relevant research. However, ResNet‐based methods ignore the importance of some large‐scale facial information and other facial age attributes. Inspired by the attention mechanism, a multi‐task learning framework for face‐based age estimation called multi‐task multi‐scale attention is proposed. First, the authors embed the alternative strategy structure of dilated convolution into ResNet34 to construct a multi‐scale attention module (MSA) to improve the network's receptive field, which extracts local age‐sensitive information while obtaining multi‐scale features. The MSA can have a larger receptive field to extract both large‐scale and local detailed feature information. Second, multi‐task learning network structures are built to predict gender and race, which can share rigid network parameters to improve age estimation and improve the accuracy of age estimation by other age‐related parameters. Finally, the Kullback‐Leibler divergence loss is adopted between a Dirac delta label and a Gaussian prediction to guide the training. The numerical tests on the MORPH Album II and Adience datasets prove the superiority of the proposed method over other state‐of‐the‐art ones.

show abstract

“…Traditional age estimation methods based on handcrafted features suffer from limited discrimina-tive power and robustness to variations in images. Deep learning models have shown significant improvements in age estimation accuracy by automatically learning dis-criminative features from facial images via Age Net & deep conditional distribution learning (DCDL) [1], [2], [3] and [4].…”

Section: Introductionmentioning

confidence: 99%

DFMFMA: Design of an efficient Deep learning model for age estimation from frontal Faces via Multimodal Feature representation & Multicomponent Augmented analysis

Jumbadkar

2023

Preprint

View full text Add to dashboard Cite

Age estimation from facial images has various applications, including security, healthcare, and entertainment. Accurate age estimation is essential for age- dependent services such as age-restricted content filtering, targeted advertising, and personalized health care. However, age estimation from facial images is a challenging task due to various factors such as variations in pose, illumination, occlusion, and aging patterns. Conventional approaches for age estimation from facial images are typically based on handcrafted features, such as texture, shape, and appearance features. These approaches often suffer from limited discriminative power and robustness to variations in the images. With the advent of deep learning, there has been a surge of interest in using deep neural networks for age estimation from facial images. Deep neural networks can learn complex and discriminative features from the images, enhancing the accuracy and robustness of the age estimation models. The proposed approach in this paper utilizes a deep learning-based approach for age estimation from frontal face images. The approach involves the analysis of facial components, including eyes, nose, and mouth, to capture age-related changes in different regions of the face images. The components are augmented using various operations such as rotation and shifting to improve the robustness of the model against variations in pose, illumination, and occlusions. The augmented components are then converted into multimodal features and individually classified using an efficient & novel Binary Cascaded CNN that employs binary weights and activations, reducing the model’s complexity and improving its efficiency levels. The use of multimodal features allows the model to capture the age-related changes in multiple domains, improving the dis- criminative efficiency of the model under multiple class scenarios. The + model’s accuracy is evaluated on augmented FGNET datasets and samples, achieving an accuracy of 99.5% with an MAE of 1.26 across all age groups. The high accuracy achieved by the proposed model highlights its effectiveness and potential for real-world age estimation scenarios.

show abstract

Deep Conditional Distribution Learning for Age Estimation

Cited by 12 publications

References 55 publications

TAA-GCN: A temporally aware Adaptive Graph Convolutional Network for age estimation

TAA-GCN: A temporally aware Adaptive Graph Convolutional Network for age estimation

Multi‐task multi‐scale attention learning‐based facial age estimation

DFMFMA: Design of an efficient Deep learning model for age estimation from frontal Faces via Multimodal Feature representation & Multicomponent Augmented analysis

Contact Info

Product

Resources

About

Deep Conditional Distribution Learning for Age Estimation

Cited by 12 publications

References 55 publications

TAA-GCN: A temporally aware Adaptive Graph Convolutional Network for age estimation

TAA-GCN: A temporally aware Adaptive Graph Convolutional Network for age estimation

Multi‐task multi‐scale attention learning‐based facial age estimation

DFMFMA: Design of an efficient Deep learning model for age estimation from frontal Faces via Multimodal Feature representation &amp; Multicomponent Augmented analysis

Contact Info

Product

Resources

About

DFMFMA: Design of an efficient Deep learning model for age estimation from frontal Faces via Multimodal Feature representation & Multicomponent Augmented analysis