108422 20230526092852.0 doi 10.1109/ICCV48922.2021.00811 sideral 124898 ART-2021-124898 eng Alonso, Iñigo Universidad de Zaragoza (orcid)0000-0003-4638-4655 Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank 2021 Access copy available to the general public Unrestricted This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach outperforms the current state-of-the-art for semi-supervised semantic segmentation and semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. info:eu-repo/grantAgreement/ES/DGA/T45-17R info:eu-repo/grantAgreement/ES/MINECO-FEDER/PGC2018-098817-A-I00 info:eu-repo/semantics/openAccess by http://creativecommons.org/licenses/by/3.0/es/ info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Sabater, Alberto Universidad de Zaragoza Ferstl, David Montesano, Luis Universidad de Zaragoza (orcid)0000-0003-1183-349X Murillo, Ana Cristina Universidad de Zaragoza (orcid)0000-0002-7580-9037 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 2021 (2021), 8219-8228 Proceedings (IEEE International Conference on Computer Vision) Proceedings (IEEE International Conference on Computer Vision) 1550-5499 2314946 http://zaguan.unizar.es/record/108422/files/texto_completo.pdf Postprint 2492209 http://zaguan.unizar.es/record/108422/files/texto_completo.jpg?subformat=icon icon Postprint https://arxiv.org/abs/2104.13415 Texto completo de la revista oai:zaguan.unizar.es:108422 articulos driver 2023-05-26-08:13:32 ARTICLE