{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:36:24Z","timestamp":1771950984709,"version":"3.50.1"},"reference-count":72,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T00:00:00Z","timestamp":1673568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004488","name":"Croatian Science Foundation","doi-asserted-by":"publisher","award":["IP-2020-02-5851 ADEPT"],"award-info":[{"award-number":["IP-2020-02-5851 ADEPT"]}],"id":[{"id":"10.13039\/501100004488","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004488","name":"Croatian Science Foundation","doi-asserted-by":"publisher","award":["KK.01.1.1.01.0009 DATACROSS"],"award-info":[{"award-number":["KK.01.1.1.01.0009 DATACROSS"]}],"id":[{"id":"10.13039\/501100004488","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Regional Development Fund","award":["IP-2020-02-5851 ADEPT"],"award-info":[{"award-number":["IP-2020-02-5851 ADEPT"]}]},{"name":"European Regional Development Fund","award":["KK.01.1.1.01.0009 DATACROSS"],"award-info":[{"award-number":["KK.01.1.1.01.0009 DATACROSS"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Semi-supervised learning is an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires substantial effort. This paper considers semi-supervised algorithms that enforce consistent predictions over perturbed unlabeled inputs. We study the advantages of perturbing only one of the two model instances and preventing the backward pass through the unperturbed instance. We also propose a competitive perturbation model as a composition of geometric warp and photometric jittering. We experiment with efficient models due to their importance for real-time and low-power applications. Our experiments show clear advantages of (1) one-way consistency, (2) perturbing only the student branch, and (3) strong photometric and geometric perturbations. Our perturbation model outperforms recent work and most of the contribution comes from the photometric component. Experiments with additional data from the large coarsely annotated subset of Cityscapes suggest that semi-supervised training can outperform supervised training with coarse labels. Our source code is available at https:\/\/github.com\/Ivan1248\/semisup-seg-efficient.<\/jats:p>","DOI":"10.3390\/s23020940","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T05:30:07Z","timestamp":1673847007000},"page":"940","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Revisiting Consistency for Semi-Supervised Semantic Segmentation"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8908-3249","authenticated-orcid":false,"given":"Ivan","family":"Grubi\u0161i\u0107","sequence":"first","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6583-2137","authenticated-orcid":false,"given":"Marin","family":"Or\u0161i\u0107","sequence":"additional","affiliation":[{"name":"Microblink Ltd., Strojarska Cesta 20, 10000 Zagreb, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7378-0536","authenticated-orcid":false,"given":"Sini\u0161a","family":"\u0160egvi\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Zhai, X., and Beyer, L. (2019, January 16\u201320). Revisiting Self-Supervised Visual Representation Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00202"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, E., Lee, S., Lee, J., and Yoon, S. (2019, January 16\u201320). FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00541"},{"key":"ref_3","unstructured":"Tarvainen, A., and Valpola, H. (2017, January 4\u20139). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","article-title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","volume":"41","author":"Miyato","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","unstructured":"Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H. (2020, January 6\u201312). Unsupervised Data Augmentation for Consistency Training. Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, Virtual."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Souly, N., Spampinato, C., and Shah, M. (2017, January 22\u201329). Semi Supervised Semantic Segmentation Using Generative Adversarial Network. Proceedings of the IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy.","DOI":"10.1109\/ICCV.2017.606"},{"key":"ref_7","unstructured":"Hung, W., Tsai, Y., Liou, Y., Lin, Y., and Yang, M. (2018, January 3\u20136). Adversarial Learning for Semi-supervised Semantic Segmentation. Proceedings of the BMVC, Newcastle, UK."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1109\/TPAMI.2019.2960224","article-title":"Semi-Supervised Semantic Segmentation with High- and Low-level Consistency","volume":"43","author":"Mittal","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","unstructured":"Cordts, M., Omran, M., Ramos, S., Scharw\u00e4chter, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2015, January 7\u201312). The Cityscapes Dataset. Proceedings of the CVPRW, Boston, MA, USA."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Rota Bul\u00f2, S., and Kontschieder, P. (2017, January 22\u201329). Mapillary Vistas Dataset for Semantic Understanding of Street Scenes. Proceedings of the ICCV, Venice, Italy.","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Maggiori, E., Tarabalka, Y., Charpiat, G., and Alliez, P. (2017, January 23\u201328). Can semantic labeling methods generalize to any city? The inria aerial image labeling benchmark. Proceedings of the 2017 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017, Fort Worth, TX, USA.","DOI":"10.1109\/IGARSS.2017.8127684"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Rota Bul\u00f2, S., Porzi, L., and Kontschieder, P. (2018, January 18\u201322). In-Place Activated BatchNorm for Memory-Optimized Training of DNNs. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00591"},{"key":"ref_13","unstructured":"Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., and Brox, T. (2014, January 8\u201313). Discriminative unsupervised feature learning with convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, hlMontreal, QC, Canada."},{"key":"ref_14","unstructured":"Salimans, T., Goodfellow, I.J., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016, January 5\u201310). Improved Techniques for Training GANs. Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Tsai, Y., Hung, W., Schulter, S., Sohn, K., Yang, M., and Chandraker, M. (2018, January 18\u201322). Learning to Adapt Structured Output Space for Semantic Segmentation. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00780"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Gao, H., Yao, D., Wang, M., Li, C., Liu, H., Hua, Z., and Wang, J. (2019). A Hyperspectral Image Classification Method Based on Multi-Discriminator Generative Adversarial Networks. Sensors, 19.","DOI":"10.3390\/s19153269"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rasmus, A., Berglund, M., Honkala, M., Valpola, H., and Raiko, T. (2015, January 7\u201312). Semi-supervised Learning with Ladder Networks. Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, Montreal, QC, Canada.","DOI":"10.1016\/j.neunet.2014.09.004"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sajjadi, M., Javanmardi, M., and Tasdizen, T. (2016, January 5\u201310). Mutual exclusivity loss for semi-supervised deep learning. Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain.","DOI":"10.1109\/ICIP.2016.7532690"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Qiao, S., Shen, W., Zhang, Z., Wang, B., and Yuille, A. (2018, January 8\u201314). Deep co-training for semi-supervised image recognition. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Bortsova, G., Dubost, F., Hogeweg, L., Katramados, I., and de Bruijne, M. (2019, January 13\u201317). Semi-supervised Medical Image Segmentation via Learning Consistency Under Transformations. Proceedings of the MICCAI, Shenzhen, China.","DOI":"10.1007\/978-3-030-32226-7_90"},{"key":"ref_21","unstructured":"Laine, S., and Aila, T. (2017, January 24\u201326). Temporal Ensembling for Semi-Supervised Learning. Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zheng, S., Song, Y., Leung, T., and Goodfellow, I.J. (2016, January 27\u201330). Improving the Robustness of Deep Neural Networks via Stability Training. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.485"},{"key":"ref_23","first-page":"1369","article-title":"Efficient ladder-style densenets for semantic segmentation of large images","volume":"40","author":"Krapac","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Grubi\u0161i\u0107, I., Or\u0161i\u0107, M., and \u0160egvi\u0107, S. (2021, January 25\u201327). A baseline for semi-supervised learning of efficient semantic segmentation models. Proceedings of the 17th International Conference on Machine Vision and Applications, MVA 2021, Aichi, Japan.","DOI":"10.23919\/MVA51890.2021.9511402"},{"key":"ref_25","unstructured":"French, G., Laine, S., Aila, T., Mackiewicz, M., and Finlayson, G. (2020, January 7\u201310). Semi-supervised semantic segmentation needs strong, varied perturbations. Proceedings of the BMVC, Virtual."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Or\u0161i\u0107, M., Kre\u0161o, I., Bevandi\u0107, P., and \u0160egvi\u0107, S. (2019, January 15\u201320). In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01289"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3381831","article-title":"Green AI","volume":"63","author":"Schwartz","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_30","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume":"Volume 9351","author":"Navab","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Proceedings of the 18th International Conference, Munich, Germany, 5\u20139 October 2015"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., and Jia, J. (2018, January 8\u201314). ICNet for Real-Time Semantic Segmentation on High-Resolution Images. Proceedings of the ECCV, Munich, Germany.","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 22\u201325). Pyramid Scene Parsing Network. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"107611","DOI":"10.1016\/j.patcog.2020.107611","article-title":"Efficient semantic segmentation with pyramidal fusion","volume":"110","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., and Wang, J. (2019, January 18\u201320). Deep High-Resolution Representation Learning for Human Pose Estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref_35","unstructured":"Chapelle, O., Schlkopf, B., and Zien, A. (2010). Semi-Supervised Learning, The MIT Press. [1st ed.]."},{"key":"ref_36","unstructured":"Saul, L.K., Weiss, Y., and Bottou, L. (2005). Semi-supervised Learning by Entropy Minimization. Proceedings of the Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yarowsky, D. (1995, January 26\u201330). Unsupervised Word Sense Disambiguation Rivaling Supervised Methods. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, Cambridge, MA, USA.","DOI":"10.3115\/981658.981684"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"McClosky, D., Charniak, E., and Johnson, M. (2006, January 4\u20139). Effective Self-Training for Parsing. Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, New York, NY, USA.","DOI":"10.3115\/1220835.1220855"},{"key":"ref_39","unstructured":"hyun Lee, D. (2013, January 16\u201321). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. Proceedings of the ICML 2013 Workshop: Challenges in Representation Learning (WREPL), Atlanta, GA, USA."},{"key":"ref_40","unstructured":"Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., and Garnett, R. (2018, January 2\u20138). Realistic Evaluation of Deep Semi-Supervised Learning Algorithms. Proceedings of the Advances in Neural Information Processing Systems 32, NeurIPS 2018, Montr\u00e9al, QC, Canada."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M., Hovy, E.H., and Le, Q.V. (2020, January 13\u201319). Self-Training With Noisy Student Improves ImageNet Classification. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, H., Shen, Y., Fei, J., Li, W., Jin, G., Wu, L., Zhao, R., and Le, X. (2022, January 18\u201324). Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"ref_43","unstructured":"Gerken, J.E., Aronsson, J., Carlsson, O., Linander, H., Ohlsson, F., Petersson, C., and Persson, D. (2021). Geometric Deep Learning and Equivariant Neural Networks. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1007\/s11263-018-1098-y","article-title":"Understanding Image Representations by Measuring Their Equivariance and Equivalence","volume":"127","author":"Lenc","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, J., Kan, M., Shan, S., and Chen, X. (2020, January 13\u201319). Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref_46","unstructured":"Cho, J.H., Mall, U., Bala, K., and Hariharan, B. (2021, January 19\u201325). PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"102374","DOI":"10.1016\/j.media.2022.102374","article-title":"Weakly supervised segmentation with cross-modality equivariant constraints","volume":"77","author":"Patel","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"H\u00e4usser, P., Mordvintsev, A., and Cremers, D. (2017, January 21\u201326). Learning by Association\u2014A Versatile Semi-Supervised Training Method for Neural Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.74"},{"key":"ref_49","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., and Raffel, C.A. (2019, January 8\u201314). MixMatch: A Holistic Approach to Semi-Supervised Learning. Proceedings of the Advances in Neural Information Processing Systems 33, NeurIPS 2019, Vancouver, BC, Canada."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Chen, X., and He, K. (2021, January 20\u201325). Exploring Simple Siamese Representation Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref_51","first-page":"10268","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","volume":"Volume 139","author":"Meila","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021"},{"key":"ref_52","unstructured":"Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H. (2020, January 6\u201312). FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, Virtual."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Qi, M., Wang, Y., Qin, J., and Li, A. (2019, January 18\u201320). KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00538"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Ouali, Y., Hudelot, C., and Tami, M. (2020, January 13\u201319). Semi-Supervised Semantic Segmentation With Cross-Consistency Training. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"ref_55","unstructured":"Zhu, Y., Zhang, Z., Wu, C., Zhang, Z., He, T., Zhang, H., Manmatha, R., Li, M., and Smola, A.J. (2020). Improving Semantic Segmentation via Self-Training. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1007\/978-3-030-58545-7_40","article-title":"Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation","volume":"Volume 12354","author":"Vedaldi","year":"2020","journal-title":"Proceedings of the Computer Vision\u2014ECCV 2020\u201416th European Conference"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Mendel, R., Souza, L., Rauber, D., Papa, J., and Palm, C. (2020, January 23\u201328). Semi-Supervised Segmentation based on Error-Correcting Supervision. Proceedings of the Computer Vision\u2014ECCV 2020\u201416th European Conference, Glasgow, UK.","DOI":"10.1007\/978-3-030-58526-6_9"},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Lai, X., Tian, Z., Jiang, L., Liu, S., Zhao, H., Wang, L., and Jia, J. (2021, January 19\u201325). Semi-supervised Semantic Segmentation with Directional Context-aware Consistency. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual.","DOI":"10.1109\/CVPR46437.2021.00126"},{"key":"ref_59","unstructured":"van den Oord, A., Li, Y., and Vinyals, O. (2018). Representation Learning with Contrastive Predictive Coding. arXiv."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 13\u201319). Momentum Contrast for Unsupervised Visual Representation Learning. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhuo, W., Qi, L., Shi, Y., and Gao, Y. (2022, January 13\u201319). ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA.","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"ref_62","unstructured":"Olah, C. (2023, January 08). Visual Information Theory. Available online: https:\/\/colah.github.io\/posts\/2015-09-Visual-Information\/."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"8704","DOI":"10.1109\/TPAMI.2019.2918284","article-title":"Convolutional Networks with Dense Connectivity","volume":"44","author":"Huang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_64","unstructured":"Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H. (2020, January 6\u201312). Bootstrap Your Own Latent\u2014A New Approach to Self-Supervised Learning. Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, Virtual."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Duchon, J. (1977). Splines minimizing rotation-invariant semi-norms in Sobolev spaces. Constructive Theory of Functions of Several Variables, Springer.","DOI":"10.1007\/BFb0086566"},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1109\/34.24792","article-title":"Principal Warps: Thin-Plate Splines and the Decomposition of Deformations","volume":"11","author":"Bookstein","year":"1989","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Szeliski, R. (2010). Computer Vision: Algorithms and Applications, Springer Science & Business Media.","DOI":"10.1007\/978-1-84882-935-0"},{"key":"ref_68","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8\u201314). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Proceedings of the Advances in Neural Information Processing Systems 33, NeurIPS 2019, Vancouver, BC, Canada."},{"key":"ref_69","unstructured":"Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H. (2020, January 6\u201312). RandAugment: Practical Automated Data Augmentation with a Reduced Search Space. Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, Virtual."},{"key":"ref_70","unstructured":"Loshchilov, I., and Hutter, F. (2017, January 24\u201326). SGDR: Stochastic Gradient Descent with Warm Restarts. Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France."},{"key":"ref_71","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., and Komodakis, N. (2016, January 19\u201322). Wide Residual Networks. Proceedings of the British Machine Vision Conference (BMVC) 2016, York, UK.","DOI":"10.5244\/C.30.87"},{"key":"ref_72","doi-asserted-by":"crossref","unstructured":"Niklaus, S., and Liu, F. (2020, January 13\u201319). Softmax Splatting for Video Frame Interpolation. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00548"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/940\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:05:23Z","timestamp":1760119523000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/940"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,13]]},"references-count":72,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["s23020940"],"URL":"https:\/\/doi.org\/10.3390\/s23020940","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,13]]}}}