Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as …
The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily …
Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against …
Y Oh, DJ Kim, IS Kweon - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
The capability of the traditional semi-supervised learning (SSL) methods is far from real- world application due to severely biased pseudo-labels caused by (1) class imbalance and …
The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization …
Y Chen, X Tan, B Zhao, Z Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of mitigating the dependence on large labeled datasets. The latest methods (eg, FixMatch) use …
Deep learning is pushing the state-of-the-art in many computer vision applications. However, it relies on large annotated data repositories, and capturing the unconstrained …
G Gui, Z Zhao, L Qi, L Zhou… - Proceedings of the …, 2023 - openaccess.thecvf.com
In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong …
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised …