Facial beauty prediction fusing transfer learning and broad learning system

Abstract

Facial beauty prediction (FBP) is an important and challenging problem in the fields of computer vision and machine learning. Not only it is easily prone to overfitting due to the lack of large-scale and effective data, but also difficult to quickly build robust and effective facial beauty evaluation models because of the variability of facial appearance and the complexity of human perception. Transfer Learning can be able to reduce the dependence on large amounts of data as well as avoid overfitting problems. Broad learning system (BLS) can be capable of quickly completing models building and training. For this purpose, Transfer Learning was fused with BLS for FBP in this paper. Firstly, a feature extractor is constructed by way of CNNs models based on transfer learning for facial feature extraction, in which EfficientNets are used in this paper, and the fused features of facial beauty extracted are transferred to BLS for FBP, called E-BLS. Secondly, on the basis of E-BLS, a connection layer is designed to connect the feature extractor and BLS, called ER-BLS. Finally, experimental results show that, compared with the previous BLS and CNNs methods existed, the accuracy of FBP was improved by E-BLS and ER-BLS, demonstrating the effectiveness and superiority of the method presented, which can also be widely used in pattern recognition, object detection and image classification.

Facial Beauty Prediction Based on Vision Transformer

“…3 show the comparison. [27] 0.2419 0.3166 0.89 ResneXt-50 [27] 0.2291 0.3017 0.8997 CNN with SCA [24] 0.2287 0.3014 0.9003 PI-CNN [44] 0.2267 0.3016 0.8978 CNN + LDL [20] 0.2201 0.294 0.9031 ResNet-18 based AaNet [45] 0.2236 0.2954 0.9055 R3CNN [28] 0.212 0.28 0.9142 CNN-ER [20] 0.2009 0.265 0.925 GPNet [18] 0 The SCUT-FBP5500 [28] data refers to a dataset specifically designed for Facial Beauty Prediction (FBP) tasks [39]. To address limitations of existing FBP datasets by offering more diversity in:…”

A Novel Deep Neural Network for Facial Beauty Improvement

“…inputting a single image and outputting the corresponding face value score) and relative value regression (i.e. inputting paired images and outputting the difference in face value scores) [41][42][43][44][45]. Differing from traditional methods, we improve the existing deep learning system for facial face value evaluation with fuzzy reasoning by the probability matrices and probabilistic semantic trust decision matrices.…”

Facial Beauty Prediction Based on Deep Learning: A Review

“…ISSN 2549-7286 (online) Gan et al [52] introduced a new approach to FBP by integrating transfer learning with a Broad Learning System (BLS). They proposed a method combining EfficientNets-based transfer learning for feature extraction and BLS for rapid model training.…”