Zero-shot Learning by Semantic Autoencoder Based on Particle Swarm Optimization Algorithm for Attribute Correlation

Nannan LU; Xinru ZHANG; Ni OU

doi:10.11999/JEIT200419

Volume 43 Issue 4

Apr. 2021

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2021 > 43(4): 982-991

Nannan LU, Xinru ZHANG, Ni OU. Zero-shot Learning by Semantic Autoencoder Based on Particle Swarm Optimization Algorithm for Attribute Correlation[J]. Journal of Electronics & Information Technology, 2021, 43(4): 982-991. doi: 10.11999/JEIT200419

Citation:

Nannan LU, Xinru ZHANG, Ni OU. Zero-shot Learning by Semantic Autoencoder Based on Particle Swarm Optimization Algorithm for Attribute Correlation[J]. Journal of Electronics & Information Technology, 2021, 43(4): 982-991. doi: 10.11999/JEIT200419

Citation:

PDF( 3844 KB)

Zero-shot Learning by Semantic Autoencoder Based on Particle Swarm Optimization Algorithm for Attribute Correlation

doi: 10.11999/JEIT200419

Nannan LU^{1
,
,},
Xinru ZHANG²,
Ni OU³

1.
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
2.
School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China
3.
School of Automation, Beijing Institute of Technology, Beijing 100081, China

Funds: The National Natural Science Foundation of China (62006233, 51734009, U1710120，51504241), The National Key Research and Development Project (2019YFE0118500)

Received Date: 2020-05-29
Rev Recd Date: 2020-12-10

Available Online: 2021-01-26

Publish Date: 2021-04-20

Abstract

Abstract

To deal with the problem of missing information caused by zero-shot image classification during building a shared attribute layer, a compensation method is proposed to embed the attribute correlation. The proposed zero-shot classification utilizes Semantic AautoEncoder (SAE) to realize the feature-to-attribute mapping, and the invisible images are classified using maximum posterior probability estimation based on the class Gaussian distribution model. In order to make up for the lack of attribute relationships in SAE learning, the additive and multiplicative factors are introduced to embed the attribute correlation. The particle swarm algorithm is used to search for the optimal factor parameters to achieve the compensation of attribute correlation information. Experimental results show that when the same mapping method is adopted, the classification performance of zero-shot image classification based on attribute correlation on Pubfig and OSR data sets is significantly improved compared with other methods.
- Zero-shot image classification,
- Relative attribute,
- SAE(Semantic AutoEncoder),
- PSO(Partial Swarm Optimization),
- Attribute correlation

FullText(HTML)

References(31)

References

LAROCHELLE H, ERHAN D, and BENGIO Y. Zero-data learning of new tasks[C]. The 23rd AAAI Conference on Artificial Intelligence, Chicago, USA, 2008: 646–651.

LAMPERT C H, NICKISCH H, and HARMELING S. Attribute-based classification for zero-shot visual object categorization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(3): 453–465. doi: 10.1109/TPAMI.2013.140

BANSAL A, SIKKA K, SHARMA G, et al. Zero-shot object detection[C]. The European Conference on Computer Vision, Munich, Germany, 2018: 397–414. doi: 10.1007/978-3-030-01246-5_24.

FU Yanwei, XIANG Tao, JIANG Yugang, et al. Recent advances in zero-shot recognition: Toward data-efficient understanding of visual content[J]. IEEE Signal Processing Magazine, 2018, 35(1): 112–125. doi: 10.1109/MSP.2017.2763441

FARHADI A, ENDRES I, HOIEM D, et al. Describing objects by their attributes[C]. 2019 IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009: 1778–1785. doi: 10.1109/CVPR.2009.5206772.

PARIKH D and GRAUMAN K. Relative attributes[C]. 2011 International Conference on Computer Vision, Barcelona, Spain, 2011: 6–13. doi: 10.1109/ICCV.2011.6126281.

CHENG Yuhu, QIAO Xue, WANG Xuesong, et al. Random forest classifier for zero-shot learning based on relative attribute[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(5): 1662–1674. doi: 10.1109/TNNLS.2017.2677441

乔雪, 彭晨, 段贺, 等. 基于共享特征相对属性的零样本图像分类[J]. 电子与信息学报, 2017, 39(7): 1563–1570. doi: 10.11999/JEIT161133

QIAO Xue, PENG Chen, DUAN He, et al. Shared features based relative attributes for zero-shot image classification[J]. Journal of Electronics &Information Technology, 2017, 39(7): 1563–1570. doi: 10.11999/JEIT161133

兰红, 方治屿. 零样本图像识别[J]. 电子与信息学报, 2020, 42(5): 1188–1200. doi: 10.11999/JEIT190485

LAN Hong and FANG Zhiyu. Recent advances in zero-shot learning[J]. Journal of Electronics &Information Technology, 2020, 42(5): 1188–1200. doi: 10.11999/JEIT190485

KODIROV E, XIANG Tao, and GONG Shaogang. Semantic autoencoder for zero-shot learning[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 4447–4456. doi: 10.1109/CVPR.2017.473.

LAMPERT C H, NICKISCH H, and HARMELING S. Learning to detect unseen object classes by between-class attribute transfer[C]. 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009: 951–958. doi: 10.1109/CVPR.2009.5206594.

KANKUEKUL P, KAWEWONG A, TANGRUAMSUB S, et al. Online incremental attribute-based zero-shot learning[C]. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 3657–3664. doi: 10.1109/CVPR.2012.6248112.

TAO Rentuo, LI Ziqiang, TAO Renshuai, et al. ResAttr-GAN: Unpaired deep residual attributes learning for multi-domain face image translation[J]. IEEE Access, 2019, 7: 132594–132608. doi: 10.1109/ACCESS.2019.2941272

冀中, 汪浩然, 于云龙, 等. 零样本图像分类综述: 十年进展[J]. 中国科学: 信息科学, 2019, 49(10): 1299–1320. doi: 10.1360/N112018-00312

JI Zhong, WANG Haoran, YU Yunlong, et al. A decadal survey of zero-shot image classification[J]. Scientia Sinica:Informationis, 2019, 49(10): 1299–1320. doi: 10.1360/N112018-00312

张鲁宁, 左信, 刘建伟. 零样本学习研究进展[J]. 自动化学报, 2020, 46(1): 1–23.

ZHANG Luning, ZUO Xin, and LIU Jianwei. Research and development on zero-shot learning[J]. Acta Automatica Sinica, 2020, 46(1): 1–23.

WANG Wei, ZHENG V W, YU Han, et al. A survey of zero-shot learning: Settings, methods, and applications[J]. ACM Transactions on Intelligent Systems and Technology, 2019, 10(2): 13. doi: 10.1145/3293318

LIU Mingxia, ZHANG Daoqiang, and CHEN Songcan. Attribute relation learning for zero-shot classification[J]. Neurocomputing, 2014, 139: 34–46. doi: 10.1016/j.neucom.2013.09.056

WANG Yang and MORI G. A discriminative latent model of object classes and attributes[C]. European Conference on Computer Vision, Berlin, Germany, 2010: 155–168. doi: 10.1007/978-3-642-15555-0_12.

BISWAS S and ANNADANI Y. Preserving semantic relations for zero-shot learning[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 7603–7612. doi: 10.1109/CVPR.2018.00793.

QUERCIA D, O’HARE N K, and CRAMER H. Aesthetic capital: What makes London look beautiful, quiet, and happy?[C]. The 17th ACM Conference on Computer Supported Cooperative Work & Social Computing, New York, USA, 2014: 945–955.

MIN Weiqing, MEI Shuhuan, LIU Linhu, et al. Multi-task deep relative attribute learning for visual urban perception[J]. IEEE Transactions on Image Processing, 2020, 29: 657–669. doi: 10.1109/TIP.2019.2932502

QIAO Lingfeng, TUO Hongya, FANG Zheng, et al. Joint probability estimation of attribute chain for zero-shot learning[C]. 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, USA, 2016: 1863–1867. doi: 10.1109/ICIP.2016.7532681.

巩萍, 程玉虎, 王雪松. 基于属性关系图正则化特征选择的零样本分类[J]. 中国矿业大学学报, 2015, 44(6): 1097–1104.

GONG Ping, CHENG Yuhu, and WANG Xuesong. Zero-shot classification based on attribute correlation graph regularized feature selection[J]. Journal of China University of Mining &Technology, 2015, 44(6): 1097–1104.

XIAO Fanyi and LEE Y J. Discovering the spatial extent of relative attributes[C]. 2015 IEEE International Conference on Computer Vision, Santiago, USA, 2015: 1458–1466. doi: 10.1109/ICCV.2015.171.

SINGH K K and LEE Y J. End-to-end localization and ranking for relative attributes[C]. European Conference on Computer Vision, Amsterdam, Netherlands, 2016: 753–769. doi: 10.1007/978-3-319-46466-4_45.

KENNEDY J and EBERHART R. Particle swarm optimization[C]. ICNN'95-International Conference on Neural Networks, Perth, Australia, 1995. doi: 10.1109/ICNN.1995.488968.

ANAMIKA, PEESAPATI R, and KUMAR N. Electricity price forecasting and classification through wavelet–dynamic weighted PSO–FFNN approach[J]. IEEE Systems Journal, 2018, 12(4): 3075–3084. doi: 10.1109/JSYST.2017.2717446

KUMAR N, BERG A C, BELHUMEUR P N, et al. Attribute and simile classifiers for face verification[C]. The 12th IEEE International Conference on Computer Vision, Kyoto, Japan, 2009: 365–372. doi: 10.1109/ICCV.2009.5459250.

OLIVA A and TORRALBA A. Modeling the shape of the scene: A holistic representation of the spatial envelope[J]. International Journal of Computer Vision, 2001, 42(3): 145–175. doi: 10.1023/A:1011139631724

LEE W H, GADER P D, and WILSON J N. Optimizing the area under a receiver operating characteristic curve with application to landmine detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(2): 389–397. doi: 10.1109/TGRS.2006.887018

CASTRO C L and BRAGA A P. Novel cost-sensitive approach to improve the multilayer perceptron performance on imbalanced data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(6): 888–899. doi: 10.1109/TNNLS.2013.2246188

Relative Articles

Supplements(0)

Cited By

Proportional views