The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks (CNNs) in creating artistic imagery by separating and recombining image content and style. This process of using CNNs to render a content image in different styles is referred to as Neural Style Transfer (NST). Since then, NST has become a trending topic both in academic literature and industrial applications. It is receiving increasing attention and a variety of approaches are proposed to either improve or extend the original NST algorithm. In this paper, we aim to provide a comprehensive overview of the current progress towards NST. We first propose a taxonomy of current algorithms in the field of NST. Then, we present several evaluation methods and compare different NST algorithms both qualitatively and quantitatively. The review concludes with a discussion of various applications of NST and open problems for future research. A list of papers discussed in this review, corresponding codes, pre-trained models and more comparison results are publicly available at: https://github.com/ycjing/Neural-Style-Transfer-Papers.
IndexTerms-Neural style transfer (NST), convolutional neural network ! Neural Style Transfer Example-Based Techniques Colour Image Analogy Texture Model-Optimisation-Based Offline Neural Methods Multiple-Style-Per-Model Neural Methods Dumoulin'17 [53] Chen'17 [54] Li'17 [55] Zhang'17 [56] Luan'17 [84] Mechrez'17 [85]Photorealistic Liao'17 [88] Attribute Champandard'16 [65] Doodle Ruder'16 [74] Video Selim'16 [73] Portrait Castillo'17 [71] Instance Gatys'17 [60] Improvement Image Gatys'16 [10] Li'17 [42] Risser'17 [44] Li'17 [45] Li'16 [46] Image Champandard'16 [65] Chen'16 [68] Mechrez'18 [69]
In this paper, we investigate a novel deep-model reusing task. Our goal is to train a lightweight and versatile student model, without human-labelled annotations, that amalgamates the knowledge and masters the expertise of two pretrained teacher models working on heterogeneous problems, one on scene parsing and the other on depth estimation. To this end, we propose an innovative training strategy that learns the parameters of the student intertwined with the teachers, achieved by "projecting" its amalgamated features onto each teacher's domain and computing the loss. We also introduce two options to generalize the proposed training strategy to handle three or more tasks simultaneously. The proposed scheme yields very encouraging results. As demonstrated on several benchmarks, the trained student model achieves results even superior to those of the teachers in their own expertise domains and on par with the state-of-the-art fully supervised models relying on human-labelled annotations.
Plant cell walls, which are mainly composed of pectin, play important roles in plant defence responses to pathogens. Pectin is synthesised in a highly esterified form and then de-esterified by pectin methylesterases (PMEs). Because of this, PMEs are directly involved in plant defence. However, the molecular mechanisms of their interactions with pectins remain unclear. In this study, we compared the expression level and enzyme activities of PMEs in a banana Cavendish cultivar (Musa AAA ‘Brazilian’) inoculated with Fusarium oxysporum f. sp. cubense pathogenic races 1 (Foc1) and 4 (Foc4). We further examined the spatial distribution of PMEs and five individual homogalacturonans (HGs) with different degree of pectin methylesterification (DM). Results suggested that the banana roots infected with Foc1 showed lower PME activity than those infected with Foc4, which was consisted with observed higher level of pectin DM. The level of HGs crosslinked with Ca2+ was significantly higher in roots infected with Foc1 compared with those infected with Foc4. Therefore, banana exhibited significantly different responses to Foc1 and Foc4 infection, and these results suggest differences in PME activities, DM of pectin and Ca2+-bridged HG production. These differences could have resulted in observed differences in virulence between Foc1 and Foc4.
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.