Search

To address the problem of reduced face recognition accuracy in masked scenarios, this paper proposes a masked face reconstruction algorithm DeMaskGAN, which uses the Transformer Reconstruction Head (TRH) to restore the masked face features, and uses the Transformer Segmentation Head as an aid so that the TRH focuses on the masked face region and reconstructs the face to an unmasked state while maintaining the identity information. To improve the model performance, identity consistency, key point consistency, and perceptual consistency supervision mechanisms for faces are proposed to assist in training the model, and data augmentation methods are used to generate Mask-FFHQ datasets adapted to the mask-obscured face segmentation and reconstruction tasks, the experimental results show that the reconstructed face images enable the face recognition algorithm MobileFaceNet to achieve an AUC metric of 0.9743, which is 0.039 better than the direct use of MobileFaceNet to recognize masked faces. [ABSTRACT FROM AUTHOR]

• A fatigue life prediction model based on cGAN has been developed. • Strain amplitude, strain rate, temperature, dissolved oxygen levels, and stacking fault energy are considered as conditions. • The prediction error of fatigue life has been reduced from five times to not higher than triple. • Probabilistic estimation of environmental fatigue life has been achieved. The thermo-mechanical-chemical coupling effect presents significant challenges in accurately predicting the fatigue life of 316 austenitic stainless steel in high-temperature and high-pressure water environments (referred to hereafter as environmental fatigue). The complexity of environmental fatigue experiments results in limited and dispersed data, further making the life prediction difficult. Traditional fatigue life prediction models are often constrained by specific loading conditions and do not adequately account for the complex environmental influences. To address these issues, this paper proposes a novel environmental fatigue life prediction model of 316 stainless steel utilizing conditional Generative Adversarial Networks. The proposed model incorporates critical environmental factors, loading conditions and stacking fault energy, allowing direct prediction of environmental fatigue life. A comparative analysis on the predicted and experimental results reveals that the cGAN-based model significantly improves the prediction accuracy, reducing the fatigue life prediction error from a factor of 5 to within 3. To quantify the uncertainty in fatigue life prediction, the Monte Carlo Dropout method is employed to enable a probabilistic assessment of fatigue life. Furthermore, four environmental and loading conditions are established to evaluate the model's extrapolation capability. The results demonstrate that the probabilistic fatigue assessment effectively captures data distribution and achieves high prediction accuracy. [ABSTRACT FROM AUTHOR]

Over the past few years, a variety of membership inference attacks against deep learning models have emerged, raising significant privacy concerns. These attacks can easily infer whether a sample exists in the training set of the target model with little adversary knowledge, and the inference accuracy is often much higher than random guessing, which causes serious privacy leakage. To this end, defenses against membership inference attacks have attracted great interest. However, the current available defense methods such as regularization, differential privacy, and knowledge distillation are unable to balance the trade‐off between privacy and utility well. In this paper, we combine knowledge distillation and generative adversarial networks to propose a novel training framework that can effectively defend against membership inference attacks, called KD‐GAN. Extensive experiments show that our method implements an attack success rate of nearly 0.5 (random guesses) which can successfully defend against membership inference attacks without causing significant damage to model utility, and consistently outperforming other defense methods in the balance of privacy and utility. [ABSTRACT FROM AUTHOR]

In order to address the problems of traditional inpainting algorithm models, such as the inability to automatically identify the specific location of the area to be restored, the cost of inpainting and the difficulty of inpainting, and the problems of structural and texture discontinuity and poor model stability in deep learning-based image inpainting, this paper proposes an image inpainting based on a contextual coherent attention. This paper designs a network model based on generative adversarial networks. First, to improve the global semantic continuity and local semantic continuity of images in image inpainting, a contextual coherent attention layer is added to the network; second, to solve the problems of slow convergence and insufficient training stability of the model, a cross-entropy loss function is used; finally, the trained generator is used to repair images. The experimental results are compared using PSNR and SSIM metrics, compared with the traditional GAN model, our model has a 3.782dB improvement in peak signal-to-noise ratio and a 0.025% improvement in structural similarity. The experimental results show that the image inpainting method in this paper has better performance in terms of image edge processing, pixel continuity and overall image structure. [ABSTRACT FROM AUTHOR]

Icon design is an important part of UI design, and a design task that designers often encounter. During the design process, it is important to highlight the function of icons themselves and avoid excessive similarity with similar icons, i.e., to have a certain degree of innovation and uniqueness. With the rapid development of deep learning technology, generative adversarial networks (GANs) can be used to assist designers in designing and updating icons. In this paper, we construct an icon dataset consisting of 8 icon categories, and introduce state-of-the-art research and training techniques including attention mechanism and spectral normalization based on the original StyleGAN. The results show that our model can effectively generate high-quality icons. In addition, based on the user study, we demonstrate that our generated icons can be useful to designers as design aids. Finally, we discuss the potential impacts and consider the prospects for future related research. [ABSTRACT FROM AUTHOR]

• A data enhancement method based on generative adversarial network is proposed. • The method combines the advantages of data augmentation and feature selection. • Case studies on a simulated case and two real industrial processes are provided. • Comparisons to state-of-the-arts show effectiveness of the proposed method. Soft sensor plays an important role in improving product quality; however, practical applications may often face with the problem of small sample size, which is challenging for developing data-driven models in terms of feature selection and good generalization. This paper proposes a data enhancement approach for small sample size data-driven problems based on generative adversarial networks integrated with maximum relevance minimum redundancy (MRMR). First, sample expansion is performed on the initial data by using a generative adversarial network. Second, irrelevant variables are eliminated by the MRMR and optimal features are obtained. Finally, neural networks-based soft sensor modeling is performed using the augmented dataset and the selected features. The proposed method is tested on a simulated penicillin case, an actual penicillin production case and an actual erythromycin production case. Experimental results show that the proposed method outperforms state-of-the-art existing methods, which verify the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]