{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:19:06Z","timestamp":1763018346924,"version":"3.41.2"},"reference-count":58,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,2,28]],"date-time":"2021-02-28T00:00:00Z","timestamp":1614470400000},"content-version":"vor","delay-in-days":58,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976076","61632007"],"award-info":[{"award-number":["61976076","61632007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Zero\u2010shot learning is dedicated to solving the classification problem of unseen categories, while generalized zero\u2010shot learning aims to classify the samples selected from both seen classes and unseen classes, in which \u201cseen\u201d and \u201cunseen\u201d classes indicate whether they can be used in the training process, and if so, they indicate seen classes, and vice versa. Nowadays, with the promotion of deep learning technology, the performance of zero\u2010shot learning has been greatly improved. Generalized zero\u2010shot learning is a challenging topic that has promising prospects in many realistic scenarios. Although the zero\u2010shot learning task has made gratifying progress, there is still a strong deviation between seen classes and unseen classes in the existing methods. Recent methods focus on learning a unified semantic\u2010aligned visual representation to transfer knowledge between two domains, while ignoring the intrinsic characteristics of visual features which are discriminative enough to be classified by itself. To solve the above problems, we propose a novel model that uses the discriminative information of visual features to optimize the generative module, in which the generative module is a dual generation network framework composed of conditional VAE and improved WGAN. Specifically, the model uses the discrimination information of visual features, according to the relevant semantic embedding, synthesizes the visual features of unseen categories by using the learned generator, and then trains the final softmax classifier by using the generated visual features, thus realizing the recognition of unseen categories. In addition, this paper also analyzes the effect of the additional classifiers with different structures on the transmission of discriminative information. We have conducted a lot of experiments on six commonly used benchmark datasets (AWA1, AWA2, APY, FLO, SUN, and CUB). The experimental results show that our model outperforms several state\u2010of\u2010the\u2010art methods for both traditional as well as generalized zero\u2010shot learning.<\/jats:p>","DOI":"10.1155\/2021\/6656797","type":"journal-article","created":{"date-parts":[[2021,2,28]],"date-time":"2021-02-28T22:35:08Z","timestamp":1614551708000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Dual Generative Network with Discriminative Information for Generalized Zero\u2010Shot Learning"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4399-7379","authenticated-orcid":false,"given":"Tingting","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8180-4697","authenticated-orcid":false,"given":"Ye","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0077-9715","authenticated-orcid":false,"given":"Xueliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,2,28]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2019.2955165"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-018-9618-1"},{"key":"e_1_2_9_3_2","first-page":"50","article-title":"Distributed differentially private average consensus for multi-agent networks by additive functional Laplace noise","volume":"62","author":"Dong T.","year":"2020","journal-title":"Journal of the Franklin Institute"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"WangM. FuW. HeX. HaoS. andWuX. A survey on large-scale machine learning IEEE Transactions on Knowledge and Data Engineering 1 1 https:\/\/doi.org\/10.1109\/TKDE.2020.3015777.","DOI":"10.1109\/TKDE.2020.3015777"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_9_6_2","article-title":"Label embedding for image classification","volume":"38","author":"Akata Z.","year":"2016","journal-title":"TPAMI-IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_9_7_2","unstructured":"Romera-ParedesB.andTorrP. H. An embarrassingly simple approach to zero-shot learning Proceedings of the 32nd International Conference on Machine Learning July 2015 Lille France."},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"XianY. LorenzT. SchieleB. andAkataZ. Feature generating networks for zero-shot learning 2018 https:\/\/arxiv.org\/abs\/1712.00981.","DOI":"10.1109\/CVPR.2018.00581"},{"key":"e_1_2_9_9_2","doi-asserted-by":"crossref","unstructured":"YeM.andGuoY. Zero-shot classification with discriminative semantic representation learning Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) July 2017 Honolulu HI USA.","DOI":"10.1109\/CVPR.2017.542"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"HeJ. HongR. LiuX. XuM. ZhaZ.-J. andWangM. Memory-augmented relation network for few-shot learning Proceedings of the 28th ACM International Conference on Multimedia October 2020 New York NY USA Association for Computing Machinery 1236\u20131244.","DOI":"10.1145\/3394171.3413811"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"AkataZ. PerronninF. HarchaouiZ. andSchmidC. Label embedding for attribute-based classification Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2013 Portland OR USA 819\u2013826.","DOI":"10.1109\/CVPR.2013.111"},{"key":"e_1_2_9_12_2","doi-asserted-by":"crossref","unstructured":"LampertC. H. NickischH. andHarmelingS. Learning to detect unseen object classes by between-class attribute transfer Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition-CVPR 2009 June 2009 Miami FL USA IEEE 951\u2013958.","DOI":"10.1109\/CVPRW.2009.5206594"},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"ChaoW.-L. ChangpinyoS. GongB. andShaF. An empirical study and analysis of generalized zero-shot learning for object recognition in the wild 2016 https:\/\/arxiv.org\/abs\/1605.04253.","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"e_1_2_9_14_2","unstructured":"XianY. LampertC. H. SchieleB. andAkataZ. Zero-shot learning-a comprehensive evaluation of the good the bad and the ugly 2018 https:\/\/arxiv.org\/abs\/1707.00600."},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"AkataZ. ReedS. WalterD. LeeH. andSchieleB. Evaluation of output embeddings for fine-grained image classification Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2015 Boston MA USA 2927\u20132936.","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"e_1_2_9_16_2","unstructured":"FromeA. CorradoG. S. ShlensJ.et al. A deep visual-semantic embedding model Proceedings of the NIPS-26th International Conference on Neural Information Processing Systems December 2013 Red Hook; NY USA."},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"KodirovE. XiangT. andGongS. Semantic autoencoder for zero-shot learning Proceedings of the CVPR-Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA.","DOI":"10.1109\/CVPR.2017.473"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"XianY. AkataZ. SharmaG. NguyenQ. HeinM. andSchieleB. Latent embeddings for zero-shot classification 2016 https:\/\/arxiv.org\/abs\/1603.08895.","DOI":"10.1109\/CVPR.2016.15"},{"key":"e_1_2_9_19_2","unstructured":"DinuG. LazaridouA. andBaroniM. Improving zero-shot learning by mitigating the hubness problem 2014 https:\/\/arxiv.org\/abs\/1412.6568."},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"ShigetoY. SuzukiI. HaraK. ShimboM. andMatsumotoY. Ridge regression hubness and zero-shot learning Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases September 2015 Berlin Germany Springer 135\u2013151.","DOI":"10.1007\/978-3-319-23528-8_9"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"ZhangL. XiangT. andGongS. Learning a deep embedding model for zero-shot learning 2017 https:\/\/arxiv.org\/abs\/1611.05088.","DOI":"10.1109\/CVPR.2017.321"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"FelixR. ReidI. andCarneiroG. Multi-modal cycle-consistent generalized zero-shot learning Proceedings of the ECCV-European Conference on Computer Vision September 2018 Munich Germany.","DOI":"10.1007\/978-3-030-01231-1_2"},{"key":"e_1_2_9_23_2","doi-asserted-by":"crossref","unstructured":"HuangHe WangC. PhilipS. Yu andWangC.-D. Generative dual adversarial network for generalized zero-shot learning Proceedings of the CVPR-Conference on Computer Vision and Pattern Recognition June 2019 Salt Lake UT USA.","DOI":"10.1109\/CVPR.2019.00089"},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"LiJ. JingM. LuKe DingZ. ZhuL. andHuangZi Leveraging the invariant side of generative zero-shot learning Proceedings of the CVPR-Conference on Computer Vision and Pattern Recognition September 2019 Salt Lake UT USA.","DOI":"10.1109\/CVPR.2019.00758"},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"XianY. SharmaS. Bernt Schiele andAkataZ. f-vaegan-d2: a feature generating framework for any-shot learning Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2019 Salt Lake UT USA.","DOI":"10.1109\/CVPR.2019.01052"},{"key":"e_1_2_9_26_2","unstructured":"GoodfellowI. Pouget-AbadieJ. MirzaM.et al. Generative adversarial nets Proceedings of the NIPS-International Conference on Neural Information Processing Systems December 2014 Washington; DC USA."},{"key":"e_1_2_9_27_2","unstructured":"MikolovT. SutskeverI. ChenK. CorradoG. S. andDeanJ. Distributed representations of words and phrases and their compositionality Proceedings of the NIPS-Neural Information Processing Systems December 2013 Lake Tahoe NV USA."},{"key":"e_1_2_9_28_2","unstructured":"ArjovskyM.andBottouL. Towards principled methods for training generative adversarial networks 2017 https:\/\/arxiv.org\/abs\/1701.04862."},{"key":"e_1_2_9_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnb.2020.2964900"},{"key":"e_1_2_9_30_2","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten L. v. d.","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_31_2","unstructured":"JayaramanD.andGraumanK. Zero-shot recognition with unreliable attributes Proceedings of the NIPS International Conference on Neural Information Processing Systems December 2014 Washington; DC USA."},{"key":"e_1_2_9_32_2","article-title":"Attributebased classification for zero-shot visual object categorization","volume":"36","author":"Lampert C.","year":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"ChangpinyoS. ChaoW.-L. GongB. andShaF. Synthesized classifiers for zero-shot learning 2016 https:\/\/arxiv.org\/abs\/1603.00550.","DOI":"10.1109\/CVPR.2016.575"},{"key":"e_1_2_9_34_2","unstructured":"NorouziM. MikolovT. BengioS.et al. Zero-shot learning by convex combination of semantic embeddings 2014 https:\/\/arxiv.org\/abs\/1312.5650."},{"key":"e_1_2_9_35_2","doi-asserted-by":"crossref","unstructured":"ZhangZ.andSaligramaV. Zero-shot learning via semantic similarity embedding 2015 https:\/\/arxiv.org\/abs\/1509.04767.","DOI":"10.1109\/ICCV.2015.474"},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"ElhoseinyM. SalehB. andElgammalA. Write a classifier: zero-shot learning using purely textual descriptions Proceedings of the ICCV-International Conference on Computer Vision December 2013 Sydney Australia.","DOI":"10.1109\/ICCV.2013.321"},{"key":"e_1_2_9_37_2","doi-asserted-by":"crossref","unstructured":"Lei BaJ. SwerskyK. FidlerS.et al. Predicting deep zeroshot convolutional neural networks using textual descriptions Proceedings of the ICCV-2015 International Conference on Computer Vision December 2015 Santiago Chile.","DOI":"10.1109\/ICCV.2015.483"},{"key":"e_1_2_9_38_2","doi-asserted-by":"crossref","unstructured":"WangX. YeY. andGuptaA. Zero-shot recognition via semantic embeddings and knowledge graphs 2018 https:\/\/arxiv.org\/abs\/1803.08035.","DOI":"10.1109\/CVPR.2018.00717"},{"key":"e_1_2_9_39_2","unstructured":"KipfT. N.andWellingM. Semi-supervised classification with graph convolutional networks Proceedings of the ICLR-International Conference on Learning Representations April 2017 Toulon France."},{"key":"e_1_2_9_40_2","unstructured":"RohrbachM. EbertS. andSchieleB. Transfer learning in a transductive setting Proceedings of the NIPS-Neural Information Processing Systems December 2013 Sierra Nevada Spain."},{"key":"e_1_2_9_41_2","doi-asserted-by":"crossref","unstructured":"VermaV. K.andRaiP. A simple exponential family framework for zero-shot learning 2017 https:\/\/arxiv.org\/abs\/1707.08040.","DOI":"10.1007\/978-3-319-71246-8_48"},{"key":"e_1_2_9_42_2","unstructured":"RadfordA. MetzL. andChintalaS. Unsupervised representation learning with deep convolutional generative adversarial networks 2016 https:\/\/arxiv.org\/abs\/1511.06434."},{"key":"e_1_2_9_43_2","unstructured":"MirzaM.andOsinderoS. Conditional generative adversarial nets 2014 https:\/\/arxiv.org\/abs\/1411.1784."},{"key":"e_1_2_9_44_2","unstructured":"ArjovskyM. ChintalaS. andBottouL. Wasserstein gan 2017 https:\/\/arxiv.org\/abs\/1701.07875."},{"key":"e_1_2_9_45_2","unstructured":"GulrajaniI. AhmedF. ArjovskyM. DumoulinV. andCourvilleA. Improved training of wasserstein gans 2017 https:\/\/arxiv.org\/abs\/1704.00028."},{"key":"e_1_2_9_46_2","doi-asserted-by":"crossref","unstructured":"ZhuJ.-Y. ParkT. IsolaP. andEfrosA. A. Unpaired imageto-image translation using cycle-consistent adversarial networks 2017 https:\/\/arxiv.org\/abs\/1703.10593.","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_2_9_47_2","doi-asserted-by":"crossref","unstructured":"SchonfeldE. EbrahimiS. SinhaS. DarrellT. andAkataZ. Generalized zero-and few-shot learning via aligned variational autoencoders 2019 https:\/\/arxiv.org\/abs\/1812.01784.","DOI":"10.1109\/CVPR.2019.00844"},{"key":"e_1_2_9_48_2","unstructured":"KingmaD. P.andWellingM. Auto-encoding variational bayes Proceedings of the ICLR-International Conference on Learning Representations April 2014 Banff AB Canada."},{"key":"e_1_2_9_49_2","doi-asserted-by":"crossref","unstructured":"NilsbackM.-E.andZissermanA. Automated flower classification over a large number of classes Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition December 2008 Bhubaneswar India.","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_2_9_50_2","unstructured":"WelinderP. BransonS. MitaT.et al. Caltech-UCSD birds 200 2010 Caltech Pasadena CA USA Technical Report CNS-TR-2010-001."},{"key":"e_1_2_9_51_2","doi-asserted-by":"crossref","unstructured":"PattersonG.andHaysJ. Sun attribute database: discovering annotating and recognizing scene attributes Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition June 2012 Providence RI USA.","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"e_1_2_9_52_2","doi-asserted-by":"crossref","unstructured":"Kumar VermaV. AroraG. MishraA. andRaiP. Generalized zero-shot learning via synthesized examples Proceedings of the CVPR-Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake UT USA.","DOI":"10.1109\/CVPR.2018.00450"},{"key":"e_1_2_9_53_2","doi-asserted-by":"crossref","unstructured":"JiangH. WangR. ShanS. andChenX. Transferable contrastive network for generalized zero-shot learning 2019 https:\/\/arxiv.org\/abs\/1908.05832.","DOI":"10.1109\/ICCV.2019.00986"},{"key":"e_1_2_9_54_2","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nfeldE. EbrahimiS. SinhaS. DarrellT. andAkataZ. Generalized zero- and few-shot learning via aligned variational autoencoders Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2019 Long Beach CA USA.","DOI":"10.1109\/CVPR.2019.00844"},{"key":"e_1_2_9_55_2","doi-asserted-by":"crossref","unstructured":"MinS. YaoH. XieH. WangC. ZhaZ.-J. andZhangY. Domain-aware visual bias eliminating for generalized zero-shot learning Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) September 2020 Seattle WA USA 12661\u201312670 https:\/\/doi.org\/10.1109\/CVPR42600.2020.01268.","DOI":"10.1109\/CVPR42600.2020.01268"},{"key":"e_1_2_9_56_2","doi-asserted-by":"crossref","unstructured":"HendricksL. A. AkataZ. RohrbachM. DonahueJ. SchieleB. andDarrellT. Generating visual explanations 3\u201319 Proceedings of the European Conference on Computer Vision August 2016 New York NY USA Springer.","DOI":"10.1007\/978-3-319-46493-0_1"},{"key":"e_1_2_9_57_2","doi-asserted-by":"crossref","unstructured":"ReedS. AkataZ. LeeH. andSchieleB. Learning deep representations of fine-grained visual descriptions 2016 https:\/\/arxiv.org\/abs\/1605.05395.","DOI":"10.1109\/CVPR.2016.13"},{"key":"e_1_2_9_58_2","doi-asserted-by":"crossref","unstructured":"XianY. SchieleB. andAkataZ. Zero-shot learning - the good the bad and the ugly 2017 https:\/\/arxiv.org\/abs\/1703.04394.","DOI":"10.1109\/CVPR.2017.328"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2021\/6656797.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2021\/6656797.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/6656797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T22:00:51Z","timestamp":1723240851000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/6656797"}},"subtitle":[],"editor":[{"given":"Chenquan","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/6656797"],"URL":"https:\/\/doi.org\/10.1155\/2021\/6656797","archive":["Portico"],"relation":{},"ISSN":["1076-2787","1099-0526"],"issn-type":[{"type":"print","value":"1076-2787"},{"type":"electronic","value":"1099-0526"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-12-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6656797"}}