{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:47:01Z","timestamp":1750308421559,"version":"3.41.0"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T00:00:00Z","timestamp":1626739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62076074, 61876044, and 61672169"],"award-info":[{"award-number":["62076074, 61876044, and 61672169"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2020A1515010670 and 2020A1515011501"],"award-info":[{"award-number":["2020A1515010670 and 2020A1515011501"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Planning Project of Guangzhou","award":["202002030141"],"award-info":[{"award-number":["202002030141"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2022,2,28]]},"abstract":"<jats:p>\n            Over the past few years, we have made great progress in image categorization based on convolutional neural networks (CNNs). These CNNs are always trained based on a large-scale image data set; however, people may only have limited training samples for training CNN in the real-world applications. To solve this problem, one intuition is augmenting training samples. In this article, we propose an algorithm called Lavagan (\n            <jats:bold>La<\/jats:bold>\n            tent\n            <jats:bold>V<\/jats:bold>\n            ariables\n            <jats:bold>A<\/jats:bold>\n            ugmentation Method based on\n            <jats:bold>G<\/jats:bold>\n            enerative\n            <jats:bold>A<\/jats:bold>\n            dversarial\n            <jats:bold>N<\/jats:bold>\n            ets) to improve the performance of CNN with insufficient training samples. The proposed Lavagan method is mainly composed of two tasks. The first task is that we augment a number latent variables (LVs) from a set of adaptive and constrained LVs distributions. In the second task, we take the augmented LVs into the training procedure of the image classifier. By taking these two tasks into account, we propose a uniform objective function to incorporate the two tasks into the learning. We then put forward an alternative two-play minimization game to minimize this uniform loss function such that we can obtain the predictive classifier. Moreover, based on Hoeffding\u2019s Inequality and Chernoff Bounding method, we analyze the feasibility and efficiency of the proposed Lavagan method, which manifests that the LV augmentation method is able to improve the performance of Lavagan with insufficient training samples. Finally, the experiment has shown that the proposed Lavagan method is able to deliver more accurate performance than the existing state-of-the-art methods.\n          <\/jats:p>","DOI":"10.1145\/3451165","type":"journal-article","created":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T21:06:18Z","timestamp":1626815178000},"page":"1-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Latent Variable Augmentation Method for Image Categorization with Insufficient Training Samples"],"prefix":"10.1145","volume":"16","author":[{"given":"Luyue","family":"Lin","sequence":"first","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guagndong Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guagndong Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guagndong Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computers, Guangdong University of Technology, Guagndong Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanshan","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computers, Guangdong University of Technology, Guagndong Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,20]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1098650"},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of the 12th International Society for Music Information Retrieval Conference. 657\u2013662","author":"And\u00e9n Joakim","year":"2011","unstructured":"Joakim And\u00e9n and St\u00e9phane Mallat . 2011 . Multiscale scattering for audio classification . In Proceedings of the 12th International Society for Music Information Retrieval Conference. 657\u2013662 . Joakim And\u00e9n and St\u00e9phane Mallat. 2011. Multiscale scattering for audio classification. In Proceedings of the 12th International Society for Music Information Retrieval Conference. 657\u2013662."},{"key":"e_1_2_1_3_1","unstructured":"Antreas Antoniou Amos Storkey and Harrison Edwards. 2017. Data augmentation generative adversarial networks. arXiv:1711.04340. Retrieved from https:\/\/arxiv.org\/abs\/1711.04340.  Antreas Antoniou Amos Storkey and Harrison Edwards. 2017. Data augmentation generative adversarial networks. arXiv:1711.04340. Retrieved from https:\/\/arxiv.org\/abs\/1711.04340."},{"key":"e_1_2_1_4_1","unstructured":"Shuai Bai Zhiqun He Tingbing Xu Zheng Zhu Yuan Dong and Hongliang Bai. 2018. Multi-hierarchical independent correlation filters for visual tracking.arXiv:1811.10302. Retrieved from https:\/\/arxiv.org\/abs\/1811.10302.  Shuai Bai Zhiqun He Tingbing Xu Zheng Zhu Yuan Dong and Hongliang Bai. 2018. Multi-hierarchical independent correlation filters for visual tracking.arXiv:1811.10302. Retrieved from https:\/\/arxiv.org\/abs\/1811.10302."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045796.3045800"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999611.2999712"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/0262-8856(95)01072-6"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68612-7_71"},{"key":"e_1_2_1_9_1","volume-title":"PCANet: A simple deep learning baseline for image classification?IEEE Transactions on Image Processing 24, 12","author":"Chan Tsung-Han","year":"2015","unstructured":"Tsung-Han Chan , Kui Jia , Shenghua Gao , Jiwen Lu , Zinan Zeng , and Yi Ma. 2015. PCANet: A simple deep learning baseline for image classification?IEEE Transactions on Image Processing 24, 12 ( 2015 ), 5017\u20135032. Tsung-Han Chan, Kui Jia, Shenghua Gao, Jiwen Lu, Zinan Zeng, and Yi Ma. 2015. PCANet: A simple deep learning baseline for image classification?IEEE Transactions on Image Processing 24, 12 (2015), 5017\u20135032."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2015.06.048"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 113\u2013123","author":"Cubuk Ekin D.","key":"e_1_2_1_11_1","unstructured":"Ekin D. Cubuk , Barret Zoph , Dandelion Mane , Vijay Vasudevan , and Quoc V. Le . 2019. Autoaugment: Learning augmentation strategies from data . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 113\u2013123 . Ekin D. Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, and Quoc V. Le. 2019. Autoaugment: Learning augmentation strategies from data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 113\u2013123."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"e_1_2_1_14_1","unstructured":"Carl Doersch. 2016. Tutorial on variational autoencoders. arXiv:1606.05908. Retrieved from https:\/\/arxiv.org\/abs\/1606.05908.  Carl Doersch. 2016. Tutorial on variational autoencoders. arXiv:1606.05908. Retrieved from https:\/\/arxiv.org\/abs\/1606.05908."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3044879"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.315"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2478256"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. 249\u2013256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio . 2010 . Understanding the difficulty of training deep feedforward neural networks . In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. 249\u2013256 . Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. 249\u2013256."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296396"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454532"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_1_25_1","volume-title":"Proceedings of the International Joint Conference on Neural Networks, 2008, part of the IEEE World Congress on Computational Intelligence, 2008","author":"Jiang Aiwen","year":"2008","unstructured":"Aiwen Jiang , Chunheng Wang , and Yuanping Zhu . 2008 . Calibrated rank-SVM for multi-label image categorization . In Proceedings of the International Joint Conference on Neural Networks, 2008, part of the IEEE World Congress on Computational Intelligence, 2008 , Hong Kong, China , June 1-6, 2008. Aiwen Jiang, Chunheng Wang, and Yuanping Zhu. 2008. Calibrated rank-SVM for multi-label image categorization. In Proceedings of the International Joint Conference on Neural Networks, 2008, part of the IEEE World Congress on Computational Intelligence, 2008, Hong Kong, China, June 1-6, 2008."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2007.903708"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00974"},{"key":"e_1_2_1_28_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A method for stochastic optimization. arXiv:1412.6980 Retrieved from https:\/\/arxiv.org\/abs\/1412.6980. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980 Retrieved from https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational bayes . In Proceedings of the International Conference on Learning Representations ( 2014 ). Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational bayes. In Proceedings of the International Conference on Learning Representations (2014)."},{"key":"e_1_2_1_30_1","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. (2009).  Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/1896300.1896315"},{"key":"e_1_2_1_33_1","first-page":"327","article-title":"On lognormal random variables: I-the characteristic function","volume":"32","author":"Leipnik Roy B.","year":"1991","unstructured":"Roy B. Leipnik . 1991 . On lognormal random variables: I-the characteristic function . The ANZIAM Journal 32 , 3 (1991), 327 \u2013 347 . Roy B. Leipnik. 1991. On lognormal random variables: I-the characteristic function. The ANZIAM Journal 32, 3 (1991), 327\u2013347.","journal-title":"The ANZIAM Journal"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/2832747.2832758"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454885"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00668"},{"key":"e_1_2_1_37_1","volume-title":"COB method with online learning for object tracking. Neurocomputing","author":"Lin Luyue","year":"2019","unstructured":"Luyue Lin , Bo Liu , and Yanshan Xiao . 2019. COB method with online learning for object tracking. Neurocomputing ( 2019 ). Luyue Lin, Bo Liu, and Yanshan Xiao. 2019. COB method with online learning for object tracking. Neurocomputing (2019)."},{"key":"e_1_2_1_38_1","unstructured":"Pengfei Liu Xipeng Qiu and Xuanjing Huang. 2017. Adversarial multi-task learning for text classification. arXiv:1704. 05742 Retrieved from https:\/\/arxiv.org\/abs\/1704.05742.  Pengfei Liu Xipeng Qiu and Xuanjing Huang. 2017. Adversarial multi-task learning for text classification. arXiv:1704. 05742 Retrieved from https:\/\/arxiv.org\/abs\/1704.05742."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/850924.851523"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISDA.2006.67"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/2029556.2029563"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354695"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2007.051000"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0539-2"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.599"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.88"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-018-0511-x"},{"key":"e_1_2_1_49_1","unstructured":"Periyasamy Rajendran and Muthusamy Madheswaran. 2010. Hybrid medical image classification using association rule mining with decision tree algorithm. arXiv:1001.3503 Retrieved from https:\/\/arxiv.org\/abs\/1001.3503.  Periyasamy Rajendran and Muthusamy Madheswaran. 2010. Hybrid medical image classification using association rule mining with decision tree algorithm. arXiv:1001.3503 Retrieved from https:\/\/arxiv.org\/abs\/1001.3503."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969635"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454761"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888089.1888106"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995504"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/36.868888"},{"key":"e_1_2_1_57_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 Retrieved from https:\/\/arxiv.org\/abs\/1409.1556.  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 Retrieved from https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/646655.700110"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248659.1248664"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/2998828.2998919"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330841"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00760"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1080\/00949655.2018.1530775"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.02.003"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0063"},{"key":"e_1_2_1_69_1","volume-title":"DADA: Deep adversarial data augmentation for extremely low data regime classification. arXiv:1809.00981","author":"Zhang Xiaofeng","year":"2018","unstructured":"Xiaofeng Zhang , Zhangyang Wang , Dong Liu , and Qing Ling . 2018 . DADA: Deep adversarial data augmentation for extremely low data regime classification. arXiv:1809.00981 Retrieved from https:\/\/arxiv.org\/abs\/1809.00981. Xiaofeng Zhang, Zhangyang Wang, Dong Liu, and Qing Ling. 2018. DADA: Deep adversarial data augmentation for extremely low data regime classification. arXiv:1809.00981 Retrieved from https:\/\/arxiv.org\/abs\/1809.00981."},{"key":"e_1_2_1_70_1","first-page":"3563","article-title":"Stacked what-where auto-encoders","volume":"15","author":"Zhao Junbo","year":"2016","unstructured":"Junbo Zhao , Michael Mathieu , Ross Goroshin , and Yann Lecun . 2016 . Stacked what-where auto-encoders . Computer Science 15 , 1 (2016), 3563 \u2013 3593 . Junbo Zhao, Michael Mathieu, Ross Goroshin, and Yann Lecun. 2016. Stacked what-where auto-encoders. Computer Science 15, 1 (2016), 3563\u20133593.","journal-title":"Computer Science"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93040-4_28"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00111"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3451165","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3451165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:25Z","timestamp":1750268965000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3451165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,20]]},"references-count":72,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2,28]]}},"alternative-id":["10.1145\/3451165"],"URL":"https:\/\/doi.org\/10.1145\/3451165","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2021,7,20]]},"assertion":[{"value":"2020-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}