Fine-Grained Age Estimation in the wild with Attention LSTM Networks

Zhang, Ke; Liu, Na; Yuan, Xingfang; Guo, Xinyao; Gao, Ce; Zhao, Zhenbing

doi:10.48550/arxiv.1805.10445

Cited by 4 publications

(6 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison, we employ only a single model and light data augmentation in testing. Moreover, our approach outperforms [17] by as much as 0.045 in terms of -error while using same backbone model, i.e., ResNet-34. In addition, the proposed approach still yields a clear performance advantage even when [17] adopts a more powerful backbone architecture, i.e., RoR-34.…”

Section: E Comparisons With State-of-the-art Methodsmentioning

confidence: 90%

“…Moreover, our approach outperforms [17] by as much as 0.045 in terms of -error while using same backbone model, i.e., ResNet-34. In addition, the proposed approach still yields a clear performance advantage even when [17] adopts a more powerful backbone architecture, i.e., RoR-34. In summary, the above comparisons demonstrate the effectiveness of the proposed methods.…”

Section: E Comparisons With State-of-the-art Methodsmentioning

confidence: 90%

“…The images are split into three subsets: a training subset comprising 2,476 images, a validation subset of 1,136 images, and a testing subset containing 1,087 images. In line with existing works [7], [17], [27], [33], [36], we merge the training and validation subsets into a larger training set and report results on the testing subset.…”

Section: A Datasetsmentioning

confidence: 99%

“…However, there are no existing works that combine both properties into one unified age encoding strategy. Moreover, other works [8], [15], [16], [17] have attempted to provide complementary information to the holistic facial image, e.g., image patches, that can be utilized to improve age estimation accuracy; this information is fused at the score- [17] or feature-level [8], [15], [16]. The downside of this strategy is that it results in additional computational cost at both the training and testing stages.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Soft-ranking Label Encoding for Robust Facial Age Estimation

Zeng

Ding

Wen

et al. 2019

Preprint

View full text Add to dashboard Cite

Automatic facial age estimation can be used in a wide range of real-world applications. However, this process is challenging due to the randomness and slowness of the aging process. Accordingly, in this paper, we propose a comprehensive framework aimed at overcoming the challenges associated with facial age estimation. First, we propose a novel age encoding method, referred to as Soft-ranking, which encodes two important properties of facial age, i.e., the ordinal property and the correlation between adjacent ages. Therefore, Soft-ranking provides a richer supervision signal for training deep models. Moreover, we also carefully analyze existing evaluation protocols for age estimation, finding that the overlap in identity between the training and testing sets affects the relative performance of different age encoding methods. Finally, since existing face databases for age estimation are generally small, deep models tend to suffer from an overfitting problem. To address this issue, we propose a novel regularization strategy to encourage deep models to learn more robust features from facial parts for age estimation purposes. Extensive experiments indicate that the proposed techniques improve the age estimation performance; moreover, we achieve state-of-the-art performance on the three most popular age databases, i.e., Morph II, CLAP2015, and CLAP2016.

show abstract

Section: E Comparisons With State-of-the-art Methodsmentioning

confidence: 90%

Section: E Comparisons With State-of-the-art Methodsmentioning

confidence: 90%

Section: A Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Soft-ranking Label Encoding for Robust Facial Age Estimation

Zeng

Ding

Wen

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, deep convolutional neural network (CNN) based approaches [17,22,30] have been commonly used for automatic age and gender classification. Generally, frontal or close to frontal face images have been used in these studies [17,18,10,34,22]. There have also been studies about gender classification from ear images [7,14,16,30,11,1,19,24,21,5] and profile face im-* The authors have equally contributed.…”

Section: Introductionmentioning

confidence: 99%

Multimodal Age and Gender Classification Using Ear and Profile Face Images

Yaman

Eyiokur

Ekenel

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

In this paper, we present multimodal deep neural network frameworks for age and gender classification, which take input a profile face image as well as an ear image. Our main objective is to enhance the accuracy of soft biometric trait extraction from profile face images by additionally utilizing a promising biometric modality: ear appearance. For this purpose, we provided end-to-end multimodal deep learning frameworks. We explored different multimodal strategies by employing data, feature, and score level fusion. To increase representation and discrimination capability of the deep neural networks, we benefited from domain adaptation and employed center loss besides softmax loss. We conducted extensive experiments on the UND-F, UND-J2, and FERET datasets. Experimental results indicated that profile face images contain a rich source of information for age and gender classification. We found that the presented multimodal system achieves very high age and gender classification accuracies. Moreover, we attained superior results compared to the state-of-the-art profile face image or ear image-based age and gender classification methods.

show abstract