{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:49:21Z","timestamp":1767340161803,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s00530-022-00931-9","type":"journal-article","created":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T10:03:49Z","timestamp":1653041029000},"page":"511-523","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Perturbation consistency and mutual information regularization for semi-supervised semantic segmentation"],"prefix":"10.1007","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8116-715X","authenticated-orcid":false,"given":"Yulin","family":"Wu","sequence":"first","affiliation":[]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Qinghe","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Hongchao","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,20]]},"reference":[{"key":"931_CR1","doi-asserted-by":"crossref","unstructured":"Liu, Z., Chen, H., Feng, R., Wu, S., Ji, S., Yang, B., Wang, X.: Deep dual consecutive network for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 525\u2013534 (2021)","DOI":"10.1109\/CVPR46437.2021.00059"},{"issue":"10","key":"931_CR2","doi-asserted-by":"publisher","first-page":"2987","DOI":"10.1109\/TNNLS.2018.2861991","volume":"30","author":"X Yang","year":"2018","unstructured":"Yang, X., Zhou, P., Wang, M.: Person reidentification via structural deep metric learning. IEEE Trans Neural Netw Learn Syst 30(10), 2987\u20132998 (2018)","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"2","key":"931_CR3","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1109\/TIP.2017.2765836","volume":"27","author":"X Yang","year":"2017","unstructured":"Yang, X., Wang, M., Tao, D.: Person re-identification with metric learning using privileged information. IEEE Trans. Image Process. 27(2), 791\u2013805 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"931_CR4","doi-asserted-by":"crossref","unstructured":"Yang, X., Wang, M., Hong, R., Tian, Q., Rui, Y.: Enhancing person re-identification in a self-trained subspace. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 13(3), 1\u201323 (2017)","DOI":"10.1145\/3089249"},{"issue":"3","key":"931_CR5","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1109\/TCSVT.2019.2893736","volume":"30","author":"X Ben","year":"2019","unstructured":"Ben, X., Gong, C., Zhang, P., Yan, R., Wu, Q., Meng, W.: Coupled bilinear discriminant projection for cross-view gait recognition. IEEE Trans. Circuits Syst. Video Technol. 30(3), 734\u2013747 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"6","key":"931_CR6","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2019.2894362","volume":"28","author":"X Ben","year":"2019","unstructured":"Ben, X., Gong, C., Zhang, P., Jia, X., Wu, Q., Meng, W.: Coupled patch alignment for matching cross-view gaits. IEEE Trans. Image Process. 28(6), 3142\u20133157 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"931_CR7","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.patcog.2019.01.017","volume":"90","author":"X Ben","year":"2019","unstructured":"Ben, X., Zhang, P., Lai, Z., Yan, R., Zhai, X., Meng, W.: A general tensor representation framework for cross-view gait recognition. Pattern Recogn. 90, 87\u201398 (2019)","journal-title":"Pattern Recogn."},{"key":"931_CR8","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, S., Jin, S., Liu, Q., Lu, S., Zimmermann, R., Cheng, L.: Towards natural and accurate future motion prediction of humans and animals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10004\u201310012 (2019)","DOI":"10.1109\/CVPR.2019.01024"},{"issue":"4","key":"931_CR9","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1109\/TMM.2016.2636750","volume":"19","author":"Z Liu","year":"2016","unstructured":"Liu, Z., Zhang, L., Liu, Q., Yin, Y., Cheng, L., Zimmermann, R.: Fusion of magnetic and visual sensors for indoor localization: Infrastructure-free and more effective. IEEE Trans. Multimedia 19(4), 874\u2013888 (2016)","journal-title":"IEEE Trans. Multimedia"},{"key":"931_CR10","doi-asserted-by":"crossref","unstructured":"Ben, X., Ren, Y., Zhang, J., Wang, S.-J., Kpalma, K., Meng, W., Liu, Y.-J.: Video-based facial micro-expression analysis: A survey of datasets, features and algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)","DOI":"10.1109\/TPAMI.2021.3067464"},{"key":"931_CR11","doi-asserted-by":"crossref","unstructured":"Chapelle, O., Scholkopf, B., Zien, A.: Semi-supervised learning (chapelle, o. et al., eds.; 2006)[book reviews]. IEEE Transactions on Neural Networks 20(3), 542\u2013542 (2009)","DOI":"10.1109\/TNN.2009.2015974"},{"key":"931_CR12","unstructured":"Lee, D.-H.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning (ICML), vol. 3, pp. 1\u20136 (2013)"},{"key":"931_CR13","unstructured":"Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242 (2016)"},{"key":"931_CR14","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems (NIPS), pp. 1195\u20131204 (2017)"},{"issue":"8","key":"931_CR15","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","volume":"41","author":"T Miyato","year":"2018","unstructured":"Miyato, T., Maeda, S.-I., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1979\u20131993 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"931_CR16","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: A holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems (NIPS), pp. 5049\u20135059 (2019)"},{"key":"931_CR17","unstructured":"Sohn, K., Berthelot, D., Li, C.-L., Zhang, Z., Carlini, N., Cubuk, E.D., Kurakin, A., Zhang, H., Raffel, C.: Fixmatch: Simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685 (2020)"},{"key":"931_CR18","unstructured":"Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: Advances in Neural Information Processing Systems (NIPS), pp. 529\u2013536 (2005)"},{"key":"931_CR19","doi-asserted-by":"crossref","unstructured":"Qi, G.-J., Zhang, L., Hu, H., Edraki, M., Wang, J., Hua, X.-S.: Global versus localized generative adversarial nets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1517\u20131525 (2018)","DOI":"10.1109\/CVPR.2018.00164"},{"issue":"2","key":"931_CR20","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1109\/TNNLS.2020.2995319","volume":"32","author":"X Li","year":"2020","unstructured":"Li, X., Yu, L., Chen, H., Fu, C.-W., Xing, L., Heng, P.-A.: Transformation-consistent self-ensembling model for semisupervised medical image segmentation. IEEE Transactions on Neural Networks and Learning Systems 32(2), 523\u2013534 (2020)","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"931_CR21","unstructured":"Hung, W.-C., Tsai, Y.-H., Liou, Y.-T., Lin, Y.-Y., Yang, M.-H.: Adversarial learning for semi-supervised semantic segmentation. arXiv preprint arXiv:1802.07934 (2018)"},{"key":"931_CR22","unstructured":"French, G., Laine, S., Aila, T., Mackiewicz, M., Finlayson, G.: Semi-supervised semantic segmentation needs strong, varied perturbations. In: British Machine Vision Conference (BMVC) (2020)"},{"key":"931_CR23","doi-asserted-by":"crossref","unstructured":"Ouali, Y., Hudelot, C., Tami, M.: Semi-supervised semantic segmentation with cross-consistency training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12674\u201312684 (2020)","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"931_CR24","doi-asserted-by":"crossref","unstructured":"Ke, Z., Di\u00a0Qiu, K.L., Yan, Q., Lau, R.W.: Guided collaborative training for pixel-wise semi-supervised learning. In: Proceedings of the European Conference on Computer Vision (ECCV), vol. 2, p. 6 (2020). Springer","DOI":"10.1007\/978-3-030-58601-0_26"},{"key":"931_CR25","doi-asserted-by":"crossref","unstructured":"Yin, Y., Liu, Z., Zimmermann, R.: Geographic information use in weakly-supervised deep learning for landmark recognition. In: 2017 IEEE International Conference on Multimedia and Expo (ICME), pp. 1015\u20131020 (2017). IEEE","DOI":"10.1109\/ICME.2017.8019376"},{"key":"931_CR26","doi-asserted-by":"crossref","unstructured":"Yang, X., Liu, X., Jian, M., Gao, X., Wang, M.: Weakly-supervised video object grounding by exploring spatio-temporal contexts. In: Proceedings of the 28th ACM International Conference on Multimedia (ACMMM), pp. 1939\u20131947 (2020)","DOI":"10.1145\/3394171.3413610"},{"key":"931_CR27","doi-asserted-by":"crossref","unstructured":"Fan, J., Zhang, Z., Song, C., Tan, T.: Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4283\u20134292 (2020)","DOI":"10.1109\/CVPR42600.2020.00434"},{"key":"931_CR28","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"931_CR29","unstructured":"Maaloe, L., Sonderby, C.K., Sonderby, S.K., Winther, O.: Auxiliary deep generative models. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 1445\u20131453 (2016)"},{"key":"931_CR30","unstructured":"Sonderby, C.K., Raiko, T., Maaloe, L., Sonderby, S.K., Winther, O.: Ladder variational autoencoders. In: Advances in Neural Information Processing Systems (NIPS), pp. 3738\u20133746 (2016)"},{"key":"931_CR31","unstructured":"Hu, W., Miyato, T., Tokui, S., Matsumoto, E., Sugiyama, M.: Learning discrete representations via information maximizing self-augmented training. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 1558\u20131567 (2017)"},{"key":"931_CR32","doi-asserted-by":"crossref","unstructured":"Qi, G.-J., Zhang, L., Chen, C.W., Tian, Q.: Avt: Unsupervised learning of transformation equivariant representations by autoencoding variational transformations. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 8130\u20138139 (2019)","DOI":"10.1109\/ICCV.2019.00822"},{"key":"931_CR33","unstructured":"Tschannen, M., Djolonga, J., Rubenstein, P.K., Gelly, S., Lucic, M.: On mutual information maximization for representation learning. arXiv preprint arXiv:1907.13625 (2019)"},{"key":"931_CR34","unstructured":"Poole, B., Ozair, S., Van Den\u00a0Oord, A., Alemi, A., Tucker, G.: On variational bounds of mutual information. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 5171\u20135180 (2019)"},{"key":"931_CR35","unstructured":"Song, J., Ermon, S.: Understanding the limitations of variational mutual information estimators. arXiv preprint arXiv:1910.06222 (2019)"},{"key":"931_CR36","unstructured":"Hjelm, R.D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Bachman, P., Trischler, A., Bengio, Y.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"931_CR37","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: Advances in Neural Information Processing Systems (NIPS), pp. 15535\u201315545 (2019)"},{"key":"931_CR38","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"931_CR39","doi-asserted-by":"crossref","unstructured":"Ji, X., Henriques, J.F., Vedaldi, A.: Invariant information clustering for unsupervised image classification and segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 9865\u20139874 (2019)","DOI":"10.1109\/ICCV.2019.00996"},{"key":"931_CR40","unstructured":"DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)"},{"issue":"12","key":"931_CR41","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2007","unstructured":"Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci. 11(12), 520\u2013527 (2007)","journal-title":"Trends Cogn. Sci."},{"key":"931_CR42","doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 648\u2013656 (2015)","DOI":"10.1109\/CVPR.2015.7298664"},{"issue":"1","key":"931_CR43","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: A retrospective. Int. J. Comput. Vision 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"931_CR44","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"931_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"931_CR46","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"931_CR47","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., Wang, Z.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"931_CR48","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 991\u2013998 (2011)","DOI":"10.1109\/ICCV.2011.6126343"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00931-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-022-00931-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00931-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T19:05:27Z","timestamp":1677524727000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-022-00931-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,20]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["931"],"URL":"https:\/\/doi.org\/10.1007\/s00530-022-00931-9","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2022,5,20]]},"assertion":[{"value":"26 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}