计算机科学 ›› 2020, Vol. 47 ›› Issue (11A): 209-214.doi: 10.11896/jsjkx.200100090
张美玉1, 刘跃辉1, 秦绪佳1, 吴良武2
ZHANG Mei-yu1, LIU Yue-hui1, QIN Xu-jia1, WU Liang-wu2
摘要： 在图像神经风格迁移(Neural Style Transfer)技术中,大多算法都存在影响视觉效果的伪影:棋盘效应与影响原图语义内容的纹理。对此,提出一种基于拉普拉斯算子抑制伪影的图像风格迁移方法。首先,使用空洞卷积、1×1卷积重新设计了快速神经风格迁移的转换网络。然后,将变换后的结果输入VGG进行特征检测,并将原图也输入VGG进行特征检测,将这两种特征进行拉普拉斯算子滤波后计算两者的L1 误差。约束图像变化,以抑制伪影。在最后的解码器阶段,使用了重新设计的网络结构,并增加了dropout的编码器来修改图像内容。在加深网络的同时,通过1×1卷积控制模型体积,将模型体积缩小了6%。实验表明了该方法抑制伪影的效果优于传统方法,其可以生成良好视觉效果的图像。
中图分类号:
| [1] GATYS L A,ECKER A S,BETHGE M.A Neural Algorithm of Artistic Style[J].arXiv:1508.06576,2015. [2] SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[C]//International Conference on Learning Representations.2015. [3] SRIVASTAVA N,HINTON G E,KRIZHEVSKY A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958. [4] MISRA D.Mish:A Self Regularized Non-Monotonic Neural Ac-tivation Function[J].arXiv:1908.08681,2019 [5] JOHNSON J,ALAHI A,FEIFEI L.Perceptual Losses for Real-Time Style Transfer and Super-Resolution[C]//European Conference on Computer Vision.2016:694-711. [6] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Computer Vision and Pattern Recognition.2015:3431-3440. [7] LUAN F,PARIS S,SHECHTMAN E,et al.Deep PainterlyHarmonization[J].Computer Graphics Forum,2018,37(4):95-106. [8] JING Y,LIU Y,YANG Y,et al.Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields[C]//European Confe-rence on Computer Vision.2018:244-260. [9] SHEN F,YAN S,ZENG G.Neural Style Transfer via MetaNetworks[C]//Computer Vision and Pattern Recognition.2018:8061-8069. [10] RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet LargeScale Visual Recognition Challenge[J].International Journal of Computer Vision,2015,115(3):211-252. [11] HE K,ZHANG X,REN S,et al.Deep Residual Learning forImage Recognition[C]//Computer Vision and Pattern Recognition.2016:770-778. [12] WANG M,WEI Q.Research on the algorithm of LaplacianSharpening[C]// Proceedings of the 16th Annual Conference on Information Theory of the Chinese Institute of Electronics.2009:464-468. [13] JIA H,ZHANG Y,LONG G,et al.REsearch on Laplace Image Enhancement Algorithm Optimization Based on OpenCL[J].Chinese Journal of Computers,2012,39(5):271. [14] YU F,KOLTUN V.Multi-Scale Context Aggregation by DilatedConvolutions[C]//International Conference on Learning Representations.2016. [15] LIN M,CHEN Q,YAN S.Network In Network[C]//International Conference on Learning Representations.2014. [16] IOFFE S,SZEGEDY C.Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift[C]//International Conference on Machine Learning.2015:448-456. [17] HINTON G E,SRIVASTAVA N,KRIZHEVSKY A,et al.Improving neural networks by preventing co-adaptation of feature detectors[J].arXiv:1207.0580,2012. [18] STEINER B,DEVITO Z,CHINTALA S,et al.PyTorch:An Imperative Style,High-Performance Deep Learning Library[C] //Neural Information Processing Systems.2019:8024-8035. [19] KINGMA D P,BA J.Adam:A Method for Stochastic Optimization[C]//International Conference on Learning Representations.2015. |
| [1] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
| [2] | 李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023 |
| [3] | 王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011 |
| [4] | 陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121 |
| [5] | 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153 |
| [6] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
| [7] | 金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190 |
| [8] | 张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036 |
| [9] | 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105 |
| [10] | 刘月红, 牛少华, 神显豪. 基于卷积神经网络的虚拟现实视频帧内预测编码 Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network 计算机科学, 2022, 49(7): 127-131. https://doi.org/10.11896/jsjkx.211100179 |
| [11] | 徐鸣珂, 张帆. Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法 Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition 计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085 |
| [12] | 孙福权, 崔志清, 邹彭, 张琨. 基于多尺度特征的脑肿瘤分割算法 Brain Tumor Segmentation Algorithm Based on Multi-scale Features 计算机科学, 2022, 49(6A): 12-16. https://doi.org/10.11896/jsjkx.210700217 |
| [13] | 吴子斌, 闫巧. 基于动量的映射式梯度下降算法 Projected Gradient Descent Algorithm with Momentum 计算机科学, 2022, 49(6A): 178-183. https://doi.org/10.11896/jsjkx.210500039 |
| [14] | 杨涵, 万游, 蔡洁萱, 方铭宇, 吴卓超, 金扬, 钱伟行. 基于步态分类辅助的虚拟IMU的行人导航方法 Pedestrian Navigation Method Based on Virtual Inertial Measurement Unit Assisted by GaitClassification 计算机科学, 2022, 49(6A): 759-763. https://doi.org/10.11896/jsjkx.211200148 |
| [15] | 王杉, 徐楚怡, 师春香, 张瑛. 基于CNN-LSTM的卫星云图云分类方法研究 Study on Cloud Classification Method of Satellite Cloud Images Based on CNN-LSTM 计算机科学, 2022, 49(6A): 675-679. https://doi.org/10.11896/jsjkx.210300177 |
|
||
首页