[1]翟永杰,张智柏,王亚茹.基于改进TransGAN的零样本图像识别方法[J].智能系统学报,2023,18(2):352-359.[doi:10.11992/tis.202111002]
ZHAI Yongjie,ZHANG Zhibai,WANG Yaru.An image recognition method of zero -shot learning based on an improved TransGAN[J].CAAI Transactions on Intelligent Systems,2023,18(2):352-359.[doi:10.11992/tis.202111002]
点击复制
ZHAI Yongjie,ZHANG Zhibai,WANG Yaru.An image recognition method of zero -shot learning based on an improved TransGAN[J].CAAI Transactions on Intelligent Systems,2023,18(2):352-359.[doi:10.11992/tis.202111002]
基于改进TransGAN的零样本图像识别方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
18
期数:
2023年第2期
页码:
352-359
栏目:
学术论文—机器感知与模式识别
出版日期:
2023-05-05
- Title:
- An image recognition method of zero -shot learning based on an improved TransGAN
- Keywords:
- zero -shot learning; generative adversarial network; TransGAN; deep learning; image recognition; image feature; convolutional layer; nonlinear activation function
- 分类号:
- TP18
- 摘要:
- 零样本学习算法旨在解决样本极少甚至缺失情况下的图像识别问题。生成式模型通过生成缺失类别的图像，将此问题转化为传统的基于监督学习的图像识别，但生成图像的质量不稳定、容易出现模式崩塌，影响图像识别准确性。为此，通过对TransGAN模型进行改进，提出基于改进TransGAN的零样本图像识别方法。将TransGAN的生成器连接卷积层进行降维，并进一步提取图像特征，使生成图像特征和真实图像特征更加接近，提高特征的稳定性；同时，对判别器加入非线性激活函数，并进行结构简化，使判别器更好地指导生成器，并减小计算量。在公共数据集上的实验结果表明，所提方法的图像识别准确率较基线模型提高了29.02%，且具有较好的泛化性能。
- Abstract:
- Zero-shot learning algorithms aim to address the challenge of image recognition with limited or even missing samples. By transforming the problem into a supervised learning task through the use of generative models, the method generates images of missing classes. However, the quality of generated images can be inconsistent and is susceptible to pattern collapse, affecting image recognition accuracy. To address this issue, we propose an improved zero-shot learning image recognition method based on an improved TransGAN. The generator of TransGAN is linked to a convolutional layer for dimensionality reduction, leading to a more effective extraction of image features and improved stability. Moreover, the addition of a nonlinear activation function to the discriminator and simplifying its structure enhances its ability to guide the generator and reduces computational requirements. Experiment results on public datasets show that our proposed method increases image recognition accuracy by 29.02% compared to the baseline model and demonstrates improved generalization performance.
- 参考文献/References:
-
[1] LAROCHELLE H, ERHAN D, BENGIO Y. Zero-data learning of new tasks[C]//AAAI’08: Proceedings of the 23rd national conference on Artificial intelligence - Volume 2. New York: ACM, 2008: 646?651.
[2] PALATUCCI M, POMERLEAU D, HINTON G, et al. Zero-shot learning with semantic output codes[C]//NIPS’09: Proceedings of the 22nd International Conference on Neural Information Processing Systems. New York: ACM, 2009: 1410?1418.
[3] XU Xing, SHEN Fumin, YANG Yang, et al. Matrix tri-factorization with manifold regularizations for zero-shot learning[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2007?2016.
[4] LIU Mingxia, ZHANG Daoqiang, CHEN Songcan. Attribute relation learning for zero-shot classification[J]. Neurocomputing, 2014, 139: 34–46.
[5] 翟永杰, 吴童桐. 基于语义空间信息映射加强的零样本学习方法[J]. 计算机应用与软件, 2020, 37(12): 113–118,196
ZHAI Yongjie, WU Tongtong. Zero shot learning based on semantic spatial information mapping enhancement[J]. Computer applications and software, 2020, 37(12): 113–118,196
[6] LAMPERT C H, NICKISCH H, HARMELING S. Learning to detect unseen object classes by between-class attribute transfer[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE, 2009: 951?958.
[7] ROMERA-PAREDES B, TORR P H S. An Embarrassingly Simple Approach to Zero-Shot Learning[M]// Visual Attributes. Cham: Springer, 2017: 11?30.
[8] QIAO Ruizhi, LIU Lingqiao, SHEN Chunhua, et al. Less is more: zero-shot learning from online textual documents with noise suppression[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2249?2257.
[9] FU Yanwei, HOSPEDALES T M, XIANG Tao, et al. Transductive multi-view zero-shot learning[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(11): 2332–2345.
[10] SHIGETO Y, SUZUKI I, HARA K, et al. Ridge regression, hubness, and zero-shot learning[M]//Machine Learning and Knowledge Discovery in Databases. Cham: Springer International Publishing, 2015: 135?151.
[11] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[J]. Advances in neural information processing systems, 2014: 27.
[12] ZHU Y, ELHOSEINY M, LIU B, et al. A generative adversarial approach for zero-shot learning from noisy texts[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City: IEEE, 2018: 1004?1013.
[13] CHEN Z, LI J, LUO Y, et al. Canzsl: Cycle-consistent adversarial networks for zero-shot learning from natural language[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Salt Lake City: IEEE, 2020: 874?883.
[14] JIANG YIFAN, CHANG SHIYU, WANG ZHANGYANG. TransGAN: two pure transformers can make one strong GAN, and that can scale up[EB/OL].(2021?02?04)[2021?10?31].https://arxiv.org/abs/2102.07074.
[15] 王正龙, 张保稳. 生成对抗网络研究综述[J]. 网络与信息安全学报, 2021, 7(4): 68–85
WANG Zhenglong, ZHANG Baowen. Survey of generative adversarial network[J]. Chinese journal of network and information security, 2021, 7(4): 68–85
[16] ADLER J, LUNZ S. Banach Wasserstein Gan[EB/OL].(2018?06?18)[2021?10?31].https://arxiv.org/abs/1806.06621.
[17] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale[EB/OL].(2020?10?22)[2021?10?31].https://arxiv.org/abs/2010.11929.
[18] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas: IEEE, 2016: 770?778.
[19] GULRAJANI I, AHMED F, ARJOVSKY M, et al. Improved training of Wasserstein GANs[EB/OL].(2017?12?25)[2020?02?02].https://arxiv.org/abs/1704.00028.
[20] XIAN Yongqin, LORENZ T, SCHIELE B, et al. Feature generating networks for zero-shot learning[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 5542?5551.
[21] NILSBACK M E, ZISSERMAN A. Automated flower classification over a large number of classes[C]//2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing. Bhubaneswar: IEEE, 2008: 722?729.
[22] WAH C, BRANSON S, WELINDER P, et al. The caltech-ucsd birds-200-2011 dataset[R]. California Institute of Technology, 2011.
[23] 刘靖祎, 史彩娟, 涂冬景, 等. 零样本图像分类综述[J]. 计算机科学与探索, 2021, 15(5): 812–824
LIU Jingyi, SHI Caijuan, TU Dongjing, et al. Survey of zero-shot image classification[J]. Journal of frontiers of computer science and technology, 2021, 15(5): 812–824
[24] ELHOSEINY M, SALEH B, ELGAMMAL A. Write a classifier: Zero-shot learning using purely textual descriptions[C]// Proceedings of the IEEE International Conference on Computer Vision. Sydney: IEEE, 2013: 2584?2591.
- 相似文献/References:
-
[1]朱文霖,刘华平,王博文,等.基于视-触跨模态感知的智能导盲系统[J].智能系统学报,2020,15(1):33.[doi:10.11992/tis.201908015]
ZHU Wenlin,LIU Huaping,WANG Bowen,et al.An intelligent blind guidance system based on visual-touch cross-modal perception[J].CAAI Transactions on Intelligent Systems,2020,15():33.[doi:10.11992/tis.201908015]
[2]毕晓君,潘梦迪.基于生成对抗网络的机载遥感图像超分辨率重建[J].智能系统学报,2020,15(1):74.[doi:10.11992/tis.202002002]
BI Xiaojun,PAN Mengdi.Super-resolution reconstruction of airborne remote sensing images based on the generative adversarial networks[J].CAAI Transactions on Intelligent Systems,2020,15():74.[doi:10.11992/tis.202002002]
[3]王昌安,田金文.生成对抗网络辅助学习的舰船目标精细识别[J].智能系统学报,2020,15(2):296.[doi:10.11992/tis.201901004]
WANG Changan,TIAN Jinwen.Fine-grained inshore ship recognition assisted by deep-learning generative adversarial networks[J].CAAI Transactions on Intelligent Systems,2020,15():296.[doi:10.11992/tis.201901004]
[4]张智,毕晓君.基于风格转换的无监督聚类行人重识别[J].智能系统学报,2021,16(1):48.[doi:10.11992/tis.202012014]
ZHANG Zhi,BI Xiaojun.Clustering approach based on style transfer for unsupervised person re-identification[J].CAAI Transactions on Intelligent Systems,2021,16():48.[doi:10.11992/tis.202012014]
[5]姜义,吕荣镇,刘明珠,等.基于生成对抗网络的人脸口罩图像合成[J].智能系统学报,2021,16(6):1073.[doi:10.11992/tis.202012010]
JIANG Yi,LYU Rongzhen,LIU Mingzhu,et al.Masked face image synthesis based on a generative adversarial network[J].CAAI Transactions on Intelligent Systems,2021,16():1073.[doi:10.11992/tis.202012010]
[6]刘万军,佟畅,曲海成.空洞卷积与注意力融合的对抗式图像阴影去除算法[J].智能系统学报,2021,16(6):1081.[doi:10.11992/tis.202011022]
LIU Wanjun,TONG Chang,QU Haicheng.An antagonistic image shadow removal algorithm based on dilated convolution and attention mechanism[J].CAAI Transactions on Intelligent Systems,2021,16():1081.[doi:10.11992/tis.202011022]
[7]吴晓东,熊伟丽.采用编码输入的生成对抗网络故障检测方法及应用[J].智能系统学报,2022,17(3):496.[doi:10.11992/tis.202102003]
WU Xiaodong,XIONG Weili.Fault detection method and its application using GAN with an encoded input[J].CAAI Transactions on Intelligent Systems,2022,17():496.[doi:10.11992/tis.202102003]
[8]严浙平,曲思瑜,邢文.水下图像增强方法研究综述[J].智能系统学报,2022,17(5):860.[doi:10.11992/tis.202108022]
YAN Zheping,QU Siyu,XING Wen.An overview of underwater image enhancement methods[J].CAAI Transactions on Intelligent Systems,2022,17():860.[doi:10.11992/tis.202108022]
[9]陈斌,朱晋宁.双流增强融合网络微表情识别[J].智能系统学报,2023,18(2):360.[doi:10.11992/tis.202109036]
CHEN Bin,ZHU Jinning.Micro-expression recognition based on a dual-stream enhanced fusion network[J].CAAI Transactions on Intelligent Systems,2023,18():360.[doi:10.11992/tis.202109036]
[10]卢娟,陈纯毅.融合递归自编解码器的蒙卡画面重构降噪方法[J].智能系统学报,2023,18(3):459.[doi:10.11992/tis.202112011]
LU Juan,CHEN Chunyi.A denoised method by fusing recursive auto-encoder decorder for Monte Carlo rendering image reconstruction[J].CAAI Transactions on Intelligent Systems,2023,18():459.[doi:10.11992/tis.202112011]
[11]张冀,曹艺,王亚茹,等.融合VAE和StackGAN的零样本图像分类方法[J].智能系统学报,2022,17(3):593.[doi:10.11992/tis.202107012]
ZHANG Ji,CAO Yi,WANG Yaru,et al.Zero-shot image classification method combining VAE and StackGAN[J].CAAI Transactions on Intelligent Systems,2022,17():593.[doi:10.11992/tis.202107012]
备注/Memo
收稿日期:2021-11-01。
基金项目:国家自然科学基金面上项目(U21A20486, 61871182)；河北省自然科学基金青年科学基金项目(F2021502008)；中央高校基本科研业务费专项资金面上项目(2021MS081).
作者简介:翟永杰,教授,博士,主要研究方向为电力视觉。主持国家自然科学基金面上项目1项,河北省自然科学基金项目1项,主持横向科研项目12项,参与国家重点研发计划项目1项,授权发明专利10项,获得山东省科技进步一等奖1项。编著1部,参编教材1部、著作3部,发表学术论文30余篇;张智柏,硕士研究生,主要研究方向为零样本学习与人工智能;王亚茹,讲师,博士,主要研究方向为模式识别与计算机视觉、数据挖掘、电力视觉。发表学术论文10余篇
通讯作者:王亚茹. E-mail：wangyaru@ncepu.edu.cn
更新日期/Last Update:
1900-01-01