doi:10.1109/ICCV48922.2021.00811engAlonso, IñigoSabater, AlbertoFerstl, DavidMontesano, LuisMurillo, Ana CristinaSemi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory BankART-2021-124898This 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.2021http://zaguan.unizar.es/record/10842210.1109/ICCV48922.2021.00811http://zaguan.unizar.es/record/108422oai:zaguan.unizar.es:108422info:eu-repo/grantAgreement/ES/DGA/T45-17Rinfo:eu-repo/grantAgreement/ES/MINECO-FEDER/PGC2018-098817-A-I00Proceedings (IEEE International Conference on Computer Vision) 2021 (2021), 8219-8228byhttp://creativecommons.org/licenses/by/3.0/es/info:eu-repo/semantics/openAccess