Generalized Pseudo-Labeling in Consistency Regularization for Semi-Supervised Learning

• Published in: 2023 IEEE International Conference on Image Processing (ICIP) pp. 525 - 529
• Main Authors: Karaliolios, Nikolaos, Chabot, Florian, Dupont, Camille, Le Borgne, Herve, Pham, Quoc-Cuong, Audigier, Romaric
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08.10.2023
• Subjects: Annotations; Benchmark testing; Consistency Regularization; Costs; Error analysis; Image processing; Pseudo-Labeling; Semantic segmentation; Semi-Supervised Learning; Semisupervised learning

Semi-Supervised Learning (SSL) reduces annotation cost by exploiting large amounts of unlabeled data. A popular idea in SSL image classification is Pseudo-Labeling (PL), where the predictions of a network are used in order to assign a label to an unlabeled image. However, this practice exposes learn...