基于空间相关性与特征级插值改进的快速图像翻译模型  

Improved Fast Image Translation Model Based on Spatial Correlation and Feature Level Interpolation

作　　者：李玉强[1] 李欢[1] 刘春[1] LI Yuqiang;LI Huan;LIU Chun(College of Computer Science and Artificial Intelligence,Wuhan University of Technology,Wuhan 435000,China)

机构地区：[1]武汉理工大学计算机与人工智能学院,武汉435000

出　　处：《计算机科学》2023年第12期156-165,共10页Computer Science

摘　　要：近年来,深度学习算法的流行使图像翻译任务取得了显著的效果。其中,很多研究工作致力于在缩短模型运行时间的同时保持图像的生成质量,ASAPNet模型就是一个典型的代表。但该模型的特征级损失函数无法完全解耦图像特征和外观,又由于其大多数计算在极低的分辨率下执行,导致生成的图像质量不够理想。针对上述问题,提出了一种基于空间相关性和特征级插值的ASAPNet改进模型——SRFIT。具体来说,根据自相似性原理,使用空间相关性损失替换原模型中的特征匹配损失,以缓解图像翻译时的场景结构差异的问题,从而提高图像翻译的准确性。此外,受ReMix中数据增强方法的启发,通过线性插值在图像特征级上增加了数据量,解决了生成器过拟合的问题。最后,在两个公开数据集CMP Facades和Cityscapes上进行对比实验,结果均表明,相比当前的主流模型,所提出的改进模型SRFIT展现了更好的性能,可以在有效改善图像生成质量的同时,保持较快的运行速度。In recent years,with the popularity of deep learning algorithms,the image translation tasks have achieved remarkable results.Many researches are devoted to reduce model running time while maintaining the quality of image generation,among which ASAPNet model is a typical representative.However,the feature level loss function of this model cannot completely decouple image features and appearance,and most of its calculations are performed at extremely low resolution,resulting in poor image quality.In response to the above issues,this paper proposes an improved ASAPNet model—SRFIT,based on spatial correlation and feature level interpolation.Specifically,according to the principle of self-similarity,the spatially-correlative loss is used to replace the feature matching loss in the original model to alleviate the problem of scene structure differences during image translation,so as to improve the accuracy of image translation.In addition,inspired by the data augmentation method in ReMix,we also increase the amount of data at the image feature level through linear interpolation,which addresses the overfitting problem of the generator.Finally,the results of comparative experiments on two public datasets,facades and cityscapes,show that compared with the current mainstream models,the proposed method shows better performance,it can effectively improve the quality of generated image while maintaining a faster running speed.

关 键 词：图像翻译 自相似性 数据增强 生成对抗网络 线性插值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]