
浏览全部资源
扫码关注微信
1.广东工业大学 信息工程学院, 广东 广州 510006
2.广东工业大学 集成电路学院 ,广东 广州 510006
[ "劳俊明(1996—),男,广东茂名人,硕士研究生,2015年于五邑大学获得学士学位,主要从事计算机视觉与深度学习方面的研究。E-mail: 1135804550@qq.com" ]
[ "叶武剑(1987—),男,广东韶关人,博士,讲师,2015年于檀国大学(Dankook University)获得博士学位,主要从事计算机视觉与深度学习、机器学习应用等方面的研究。E-mail: yewjian@126.com" ]
收稿日期:2021-11-24,
修回日期:2022-01-06,
纸质出版日期:2022-06-05
移动端阅览
劳俊明, 叶武剑, 刘怡俊, 等. 基于双专用注意力机制引导的循环生成对抗网络[J]. 液晶与显示, 2022,37(6):746-757.
Jun-ming LAO, Wu-jian YE, Yi-jun LIU, et al. Cycle generative adversarial network guided by dual special attention mechanism[J]. Chinese journal of liquid crystals and displays, 2022, 37(6): 746-757.
劳俊明, 叶武剑, 刘怡俊, 等. 基于双专用注意力机制引导的循环生成对抗网络[J]. 液晶与显示, 2022,37(6):746-757. DOI: 10.37188/CJLCD.2021-0293.
Jun-ming LAO, Wu-jian YE, Yi-jun LIU, et al. Cycle generative adversarial network guided by dual special attention mechanism[J]. Chinese journal of liquid crystals and displays, 2022, 37(6): 746-757. DOI: 10.37188/CJLCD.2021-0293.
现有基于循环生成对抗网络的图像生成方法通过引入独立通用的注意力模块,在无匹配图像转换任务中取得了较好的效果,但同时也增加了模型复杂度与训练时间,而且难以关注到图中关键区域的所有细节,图像生成效果仍有提升的空间。针对上述问题,提出一种基于双专用注意力机制引导的循环生成对抗网络(Dual-SAG-CycleGAN),分别对生成器和判别器采用不同的注意力机制进行引导。首先,提出一种名为SAG(Special Attention-mechanism Guided)的专用注意力模块来引导生成器工作,在提升生成图像质量的同时降低网络的复杂度;然后,对判别器采用基于CAM(Class Activation Mapping)的专用注意力机制引导模块,抑制生成器生成无关的噪声;最后,提出背景掩码的循环一致性损失函数,引导生成器生成更加精准的掩码图,更好地辅助图像转换。实验证明,本文方法与现有同类模型相比,网络模型参数量降低近32.8%,训练速度快34.5%,KID与FID最低分别可达1.13和57.54,拥有更高的成像质量。
The existing image generation methods based on cycle generative adversarial network have achieved excellent results in unpaired image to image translation tasks by introducing a separate generic attention module, but they also increase the model complexity and training time, and it is difficult to focus on all the details of key regions in the image, and there is still room for improvement in image generation results. To solve these problems, this paper proposes a dual special attention-mechanism guided cycle generative adversarial network architecture for unpaired image transformation translation (Dual-SAG-CycleGAN). Firstly, to improve the quality of the generated images and reduce the complexity of the network, a special attention module called SAG (Special Attention-mechanism Guided) is proposed to guide the generator. Then, to suppress the generation of extraneous noise by the generator, a discriminator based on special attention mechanism of CAM (Class Activation Mapping)is introduced. Finally, a cyclic consistency loss function for the background mask is introduced to guide the network to generate a more accurate mask map, which can better aid for image translation. Experiments demonstrate that compared with similar existing models, our proposed method can reduce the maximum number of parameters by 32.8%, speed of train 34.5% faster, and generate higher quality images with a minimum KID and FID of 1.13 and 57.54, respectively.
陈宗航 , 胡海龙 , 姚剑敏 , 等 . 基于改进生成对抗网络的单帧图像超分辨率重建 [J]. 液晶与显示 , 2021 , 36 ( 5 ): 705 - 712 . doi: 10.37188/CJLCD.2020-0250 http://dx.doi.org/10.37188/CJLCD.2020-0250
CHEN Z H , HU H L , YAO J M , et al . Single frame image super-resolution reconstruction based on improved generative adversarial network [J]. Chinese Journal of Liquid Crystals and Displays , 2021 , 36 ( 5 ): 705 - 712 . (in Chinese) . doi: 10.37188/CJLCD.2020-0250 http://dx.doi.org/10.37188/CJLCD.2020-0250
KARRAS T , LAINE S , AILA T . A style-based generator architecture for generative adversarial networks [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Long Beach : IEEE , 2019 : 4396 - 4405 . doi: 10.1109/cvpr.2019.00453 http://dx.doi.org/10.1109/cvpr.2019.00453
CAO Y , ZHOU Z M , ZHANG W N , et al . Unsupervised diverse colorization via generative adversarial networks [C]// European Conference on Machine Learning and Knowledge Discovery in Databases . Skopje : Springer , 2017 : 151 - 166 . doi: 10.1007/978-3-319-71249-9_10 http://dx.doi.org/10.1007/978-3-319-71249-9_10
周文舟 , 范晨 , 胡小平 , 等 . 多尺度奇异值分解的偏振图像融合去雾算法与实验 [J]. 中国光学 , 2021 , 14 ( 2 ): 298 - 306 . doi: 10.37188/CO.2020-0099 http://dx.doi.org/10.37188/CO.2020-0099
ZHOU W Z , FAN C , HU X P , et al . Multi-scale singular value decomposition polarization image fusion defogging algorithm and experiment [J]. Chinese Optics , 2021 , 14 ( 2 ): 298 - 306 . (in Chinese) . doi: 10.37188/CO.2020-0099 http://dx.doi.org/10.37188/CO.2020-0099
GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial networks [C]// Advances in Neural Information Processing Systems (NeurIPS) . Cambridge, MA : MIT Press , 2014 : 2672 - 2680 .
ISOLA P , ZHU J Y , ZHOU T H , et al . Image-to-image translation with conditional adversarial networks [C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Honolulu : IEEE , 2017 : 5967 - 5976 . doi: 10.1109/cvpr.2017.632 http://dx.doi.org/10.1109/cvpr.2017.632
YI Z L , ZHANG H , TAN P , et al . DualGAN: unsupervised dual learning for image-to-image translation [C]// IEEE International Conference on Computer Vision (ICCV) . Venice : IEEE , 2017 : 2868 - 2876 . doi: 10.1109/iccv.2017.310 http://dx.doi.org/10.1109/iccv.2017.310
KIM T , CHA M , KIM H , et al . Learning to discover cross-domain relations with generative adversarial networks [C]// Proceedings of the 34th International Conference on Machine Learning (ICML) . Sydney : ACM , 2017 : 1857 - 1865 . doi: 10.1109/iccvw.2017.229 http://dx.doi.org/10.1109/iccvw.2017.229
LIU M Y , BREUEL T , KAUTZ J . Unsupervised image-to-image translation networks [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach : ACM , 2017 : 700 - 708 .
HUANG X , LIU M Y , BELONGIE S , et al . Multimodal unsupervised image-to-image translation [C]// 15th European Conference on Computer Vision (ECCV) . Munich : Springer , 2018 : 179 - 196 . doi: 10.1007/978-3-030-01219-9_11 http://dx.doi.org/10.1007/978-3-030-01219-9_11
LEE H Y , TSENG H Y , HUANG J B , et al . Diverse image-to-image translation via disentangled representations [C]// 15th European Conference on Computer Vision (ECCV) . Munich : Springer , 2018 : 36 - 52 . doi: 10.1007/978-3-030-01246-5_3 http://dx.doi.org/10.1007/978-3-030-01246-5_3
ZHU J Y , PARK T , ISOLA P , et al . Unpaired image-to-image translation using cycle-consistent adversarial networks [C]// IEEE International Conference on Computer Vision (ICCV) . Venice : IEEE , 2017 : 2242 - 2251 . doi: 10.1109/iccv.2017.244 http://dx.doi.org/10.1109/iccv.2017.244
MEJJATI Y A , RICHARDT C , TOMPKIN J , et al . Unsupervised attention-guided image-to-image translation [C]// Advances in Neural Information Processing Systems (NeurIPS) . Cambridge, MA : MIT Press , 2018 : 3697 - 3707 .
CHEN X Y , XU C , YANG X K , et al . Attention-GAN for object transfiguration in wild images [C]// 15th European Conference on Computer Vision (ECCV) . Munich : Springer , 2018 : 167 - 184 . doi: 10.1007/978-3-030-01216-8_11 http://dx.doi.org/10.1007/978-3-030-01216-8_11
YANG C , KIM T , WANG R Z , et al . Show, attend, and translate: unsupervised image translation with self-regularization and attention [J]. IEEE Transactions on Image Processing , 2019 , 28 ( 10 ): 4845 - 4856 . doi: 10.1109/tip.2019.2914583 http://dx.doi.org/10.1109/tip.2019.2914583
TANG H , XU D , SEBE N , et al . Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation [C]// International Joint Conference on Neural Networks (IJCNN) . Budapest : IEEE , 2019 : 1 - 8 . doi: 10.1109/ijcnn.2019.8851881 http://dx.doi.org/10.1109/ijcnn.2019.8851881
KIM J , KIM M , KANG H , et al . U-GAT-IT: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation [C]// International Conference on Learning Representations (ICLR) . Berlin : ICLR , 2020 .
ZHOU B L , KHOSLA A , LAPEDRIZA A , et al . Learning deep features for discriminative localization [C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Las Vegas : IEEE , 2016 : 2921 - 2929 . doi: 10.1109/cvpr.2016.319 http://dx.doi.org/10.1109/cvpr.2016.319
WANG F , JIANG M Q , QIAN C , et al . Residual attention network for image classification [C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Honolulu : IEEE , 2017 : 6450 - 6458 . doi: 10.1109/cvpr.2017.683 http://dx.doi.org/10.1109/cvpr.2017.683
MA S , FU J L , CHEN C W , et al . DA-GAN: Instance-level image translation by deep attention generative adversarial networks [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Salt Lake City : IEEE , 2018 : 5657 - 5666 . doi: 10.1109/cvpr.2018.00593 http://dx.doi.org/10.1109/cvpr.2018.00593
WU W , CAO K D , LI C , et al . TransGaGa: geometry-aware unsupervised image-to-image translation [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Long Beach : IEEE , 2019 : 8004 - 8013 . doi: 10.1109/cvpr.2019.00820 http://dx.doi.org/10.1109/cvpr.2019.00820
BIŃKOWSKI M , SUTHERLAND D J , ARBEL M , et al . Demystifying MMD GANs [C]// International Conference on Learning Representations (ICLR) . Berlin, German : ICLR , 2018 : 871 - 878 .
HEUSEL M , RAMSAUER H , UNTERTHINER T , et al . GANs trained by a two time-scale update rule converge to a local nash equilibrium [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach : ACM , 2017 : 6629 - 6640 . doi: 10.48550/arXiv.1706.08500 http://dx.doi.org/10.48550/arXiv.1706.08500
0
浏览量
268
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621