Label Distribution-Based Facial Attractiveness Computation by Deep Residual Learning

Fan, Yangyu; Liu, Shu; Li, Bo; Guo, Zhe; Samal, Ashok; Wan, Jun; Li, Stan Z.

doi:10.1109/tmm.2017.2780762

Cited by 60 publications

(41 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, we demonstrate that using our model to select the best dating photos is as accurate as having 10 humans vote on each photo and selecting the best average score. Architecture SCUT-FBP Best Run SCUT-FBP 5 Fold CV HotOrNot MLP [18] 76 71 -AlexNet-1 [42] 90 84 -AlexNet-2 [42] 92 88 -PI-CNN [18] 87 86 -CF [17] 88 --LDL [41] 93 --DRL [25] 93 --MT-CNN [42] 92 90 -CR-Net [22] 87 -48. Through this work, we also conclude that Photofeeler's normalizing and weighting algorithm dramatically decreases noise in the votes.…”

Section: Resultsmentioning

confidence: 99%

“…Anderson et al [24] benchmark a variety of CNN architectures on the CelebA dataset for binary attractiveness prediction. Both Fan et al [41] and Liu et al [25] propose replacing the regression output with a distribution prediction output and using a KL-Divergence loss rather than the standard mean squared error. We adopt a similar architecture to this.…”

Section: Related Workmentioning

confidence: 99%

“…We believe this leads to improved performance because the gradients are smoother for cross-entropy loss. Distribution modeling [41,25] with weights, as described in section 3.2.2, gives more information to the model. Rather than a single number, it gives a discrete distribution over the votes for the input image.…”

Section: Hyperparameter Selectionmentioning

confidence: 99%

See 2 more Smart Citations

Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction

Kalra¹,

Peterson²

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

In just a few years, online dating has become the dominant way that young people meet to date, making the deceptively error-prone task of picking good dating profile photos vital to a generation's ability to form romantic connections. Until now, artificial intelligence approaches to Dating Photo Impression Prediction (DPIP) have been very inaccurate, unadaptable to real-world application, and have only taken into account a subject's physical attractiveness. To that effect, we propose Photofeeler-D3 -the first convolutional neural network as accurate as 10 human votes for how smart, trustworthy, and attractive the subject appears in highly variable dating photos. Our "attractive" output is also applicable to Facial Beauty Prediction (FBP), making Photofeeler-D3 state-of-the-art for both DPIP and FBP. We achieve this by leveraging Photofeeler's Dating Dataset (PDD) with over 1 million images and tens of millions of votes, our novel technique of voter modeling, and cutting-edge computer vision techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction

Kalra¹,

Peterson²

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…Hence, it is very important to use another algorithm to improve the detection accuracy. Previously, Fan et al proposed using a deep residual network to enhance the automatic learning of hierarchical aesthetics representation; they found that network performance increased with the number of layers [34,35]. For this reason, we tried adding a layer of fully connected layers that are based on the YOLO network and used the dropout function to prevent overfitting.…”

Section: Algorithm Optimizationmentioning

confidence: 99%

Investigation of a Promoted You Only Look Once Algorithm and Its Application in Traffic Flow Monitoring

et al. 2019

View full text Add to dashboard Cite

We propose a high-performance algorithm while using a promoted and modified form of the You Only Look Once (YOLO) model, which is based on the TensorFlow framework, to enhance the real-time monitoring of traffic-flow problems by an intelligent transportation system. Real-time detection and traffic-flow statistics were realized by adjusting the network structure, optimizing the loss function, and introducing weight regularization. This model, which we call YOLO-UA, was initialized based on the weight of a YOLO model pre-trained while using the VOC2007 data set. The UA-CAR data set with complex weather conditions was used for training, and better model parameters were selected through tests and subsequent adjustments. The experimental results showed that, for different weather scenarios, the accuracy of the YOLO-UA was ~22% greater than that of the YOLO model before optimization, and the recall rate increased by about 21%. On both cloudy and sunny days, the accuracy, precision, and recall rate of the YOLO-UA model were more than 94% above the floating rate, which suggested that the precision and recall rate achieved a good balance. When used for video testing, the YOLO-UA model yielded traffic statistics with an accuracy of up to 100%; the time to count the vehicles in each frame was less than 30 ms and it was highly robust in response to changes in scenario and weather.

show abstract

“…The Northeast China database [22], Shanghai database [21], Hot-Or-Not database [32], [33], AVA database [16] and re-sampled face subset of AVA database [34] are large-scale databases involved with FBP, where the Northeast China [22] and Shanghai database [21] are limited for geometric facial beauty analysis without attractiveness ratings; Hot-Or-Not database [32], [33] only focuses on the appearance-based FBP; and the AVA database [16], [34] is originally designed for aesthetic analysis of entire images but not the facial attractiveness. In our previous work, Xie et al [1] published a SCUT-FBP benchmark dataset, which has led to many FBP models [1]- [3], [31], [37], especially the hierarchial CNN-based FBP models with the state-of-the-art deep learning [1]- [3], [37]. Despite the prevalent usage of the SCUT-FBP, it only contains 500 Asian Female faces, which may limit the performance of the datademanded model for FBP.…”

Section: Introductionmentioning

confidence: 99%

SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction

Liang

Lin

Jin

et al. 2018

2018 24th International Conference on Pattern Recognition (ICPR)

146

110

View full text Add to dashboard Cite

Facial beauty prediction (FBP) is a significant visual recognition problem to make assessment of facial attractiveness that is consistent to human perception. To tackle this problem, various data-driven models, especially state-of-the-art deep learning techniques, were introduced, and benchmark dataset become one of the essential elements to achieve FBP. Previous works have formulated the recognition of facial beauty as a specific supervised learning problem of classification, regression or ranking, which indicates that FBP is intrinsically a computation problem with multiple paradigms. However, most of FBP benchmark datasets were built under specific computation constrains, which limits the performance and flexibility of the computational model trained on the dataset. In this paper, we argue that FBP is a multi-paradigm computation problem, and propose a new diverse benchmark dataset, called SCUT-FBP5500, to achieve multi-paradigm facial beauty prediction. The SCUT-FBP5500 dataset has totally 5500 frontal faces with diverse properties (male/female, Asian/Caucasian, ages) and diverse labels (face landmarks, beauty scores within [1,5], beauty score distribution), which allows different computational models with different FBP paradigms, such as appearance-based/shape-based facial beauty classification/regression model for male/female of Asian/Caucasian. We evaluated the SCUT-FBP5500 dataset for FBP using different combinations of feature and predictor, and various deep learning methods. The results indicates the improvement of FBP and the potential applications based on the SCUT-FBP5500.

show abstract

Label Distribution-Based Facial Attractiveness Computation by Deep Residual Learning

Cited by 60 publications

References 34 publications

Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction

Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction

Investigation of a Promoted You Only Look Once Algorithm and Its Application in Traffic Flow Monitoring

SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction

Contact Info

Product

Resources

About