Because of the lack of discriminative face representations and scarcity of labeled training data, facial beauty prediction (FBP), which aims at assessing facial attractiveness automatically, has become a challenging pattern recognition problem. Inspired by recent promising work on fine-grained image classification using the multiscale architecture to extend the diversity of deep features, BeautyNet for unconstrained facial beauty prediction is proposed in this paper. Firstly, a multiscale network is adopted to improve the discriminative of face features. Secondly, to alleviate the computational burden of the multiscale architecture, MFM (max-feature-map) is utilized as an activation function which can not only lighten the network and speed network convergence but also benefit the performance. Finally, transfer learning strategy is introduced here to mitigate the overfitting phenomenon which is caused by the scarcity of labeled facial beauty samples and improves the proposed BeautyNet’s performance. Extensive experiments performed on LSFBD demonstrate that the proposed scheme outperforms the state-of-the-art methods, which can achieve 67.48% classification accuracy.
Facial beauty prediction (FBP) has become an emerging area in the field of artificial intelligence. However, the lacks of data and accurate face representation hinder the development of FBP. Multi-task transfer learning can effectively avoid over-fitting, and utilize auxiliary information of related tasks to optimize the main task. In this paper, we present a network named Multi-input Multi-task Beauty Network (2M BeautyNet) and use transfer learning to predict facial beauty. In the experiment, beauty prediction is the main task, and gender recognition is the auxiliary. For multi-task training, we employ multitask loss weights automatic learning strategy to improve the performance of FBP. Finally, we replace the softmax classifier with a random forest. We conduct experiments on the Large Scale Facial Beauty Database (LSFBD) and SCUT-FBP5500 database. Results show that our method has achieved good results on LSFBD, the accuracy of FBP is up to 68.23%. Our 2M BeautyNet structure is suitable for multiple inputs of different databases. INDEX TERMS Facial beauty prediction, multi-task transfer learning, multi-input multi-output network, multi-task loss weight automatic learning strategy.
This paper aims to explain the design of a novel time-varying sliding mode control of variable parameter (VP-TVSMC), which can effectively solve the anti-swing and positioning problem of distributed-mass double pendulum bridge crane system with its quick responsiveness and strong robustness to external interference. More specifically, this model initiates with the establishment of the dynamic equation of double pendulum crane model based on distributed-mass, then followed by the design of a time-varying parameter to realize the dynamic adjustment of the sliding mode surface and enhance the adjustment ability of the sliding mode surface, which is conducive to the global robustness of the double pendulum crane system under VP-TVSMC. With Lyapunov method and LaSalle's invariance principle, the asymptotic stability of the system can be sufficiently proved. Finally, the adoption of three kinds of external interference signals and uncertain system parameters successfully verified the preeminent control performance and global robustness against external interference of the proposed controller. The simulation results indicate that compared with the conventional CSMC, the proposed control method can reduce the driving force of the trolley, ensure the rapid and precise positioning of the trolley, as well as restrain the load swing angle within 5° in an effective manner. In addition, compared with the symbolic function sgn(S), the designed continuous function th(S) possesses a better anti-chattering effect, thus strengthening of the control performance of VP-TVSMC.INDEX TERMS Bridge crane, distributed-mass, time-varying sliding mode control, LaSalle's invariance principle, asymptotic stability, global robustness.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.