首页|Findings from Network Information Center in Computational Intelligence Reported (Style Migration Based on the Loss Function of Location Information)
Findings from Network Information Center in Computational Intelligence Reported (Style Migration Based on the Loss Function of Location Information)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on co mputational intelligence. According to news reporting out of Shaanxi, People’s R epublic of China, by NewsRx editors, research stated, “Using the improved Johnso n et al.’s style migration network as a starting point, this paper proposes a ne w loss function based on the position information Gram matrix.” Our news journalists obtained a quote from the research from Network Information Center: “The new method adds the chunked Gram matrix with position information, and simultaneously, the structural similarity between the style map and the res ultant image is added to the style training. The style position information is g iven to the resultant image, and finally, the resolution of the resultant image is improved with the SRGAN. The new model can effectively migrate the texture st ructure as well as the color space of the style image, while the data of the con tent image are kept intact. The simulation results reveal that the image process ing results of the new model improve those of the classical Johnson et al.’s met hod, Google Brain team method, and CCPL method, and the SSIM values of the resul ting map and style image are all greater than 0.3. As a comparison, the SSIM val ues of Johnson et al., Google Brain team, and CCPL are 0.14, 0.11, and 0.12, res pectively, which is an obvious improvement.”
Network Information CenterShaanxiPeo ple’s Republic of ChinaAsiaComputational IntelligenceMachine Learning
NETL
NSTL
