Abstract Shenzhen is a modern metropolis, but it hides variety of valuable cultural heritage, such as ancient murals. How to effectively preserve and repair the murals worthy discussion question. Here, we propose generation-discriminator network model based on artificial intelligence algorithms perform digital image restoration damaged In adversarial learning, this study optimizes discriminativ...

The recognition of human tRNA(Leu) or tRNA(Ser) by cognate aminoacyl- tRNA synthetases has distinct requirements. Only one base change (A73-->G) in tRNA(Leu) is required to generate an efficient serine acceptor in vitro, whereas several changes in three structural domains (the acceptor stem, DHU loop and long extra arm) of tRNA(Ser) are necessary in order to produce a leucine acceptor. Hence, t...

Network Design: The architecture of GeoConGAN is based on the CycleGAN [13], i.e. we train two conditional generator and two discriminator networks for synthetic and real images, respectively. Recently, also methods using only one generator and discriminator for enrichment of synthetic images from unpaired data have been proposed. Shrivastava et al. [9] and Liu et al. [5] both employ an L1 loss...

Generative adversarial training can be generally understood as minimizing certain moment matching loss defined by a set of discriminator functions, typically neural networks. The discriminator set should be large enough to be able to uniquely identify the true distribution (discriminative), and also be small enough to go beyond memorizing samples (generalizable). In this paper, we show that a d...

The discriminator of an integer sequence s = (s(i))i≥0, introduced by Arnold, Benkoski, and McCabe in 1985, is the map Ds(n) that sends n ≥ 1 to the least positive integer m such that the n numbers s(0), s(1), . . . , s(n − 1) are pairwise incongruent modulo m. In this note we consider the discriminators of a certain class of sequences, the k-regular sequences. We compute the discriminators of ...

We propose a method 1 for semi-supervised semantic segmentation using the adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully convolutional manner to differentiate the predicted probability maps from the ground truth segmentation distribution with the consideration of the spatial re...

Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize output with rich structures such as natural language descriptions. In this paper, we propose a novel generative adversarial network, RankGAN, for generating high...

• Laser vibration sensing has traditionally relied on limiters and &equencymodulation (FM) discriminators to process frequency-modulated laser radar returns. The performance of the traditional FM-discriminator approach can be limited by laser signature characteristics; both the temporal coherence of the laser and t~'get speckle can degrade the performance of an FM-discriminatorbased laser vibra...