Results 21 to 30 of about 601,753 (327)
Complementary consistency semi-supervised learning for 3D left atrial image segmentation [PDF]
Comput. Biol. Medicine, 2022 A network based on complementary consistency training, CC-Net, has been proposed for semi-supervised left atrium image segmentation. CC-Net efficiently utilizes unlabeled data from the perspective of complementary information, addressing the limited ...
Hejun Huang +4 more
semanticscholar +1 more source
Semi-supervised learning [PDF]
Machine Learning, 1989 The distribution-independent model of (supervised) concept learning due to Valiant (1984) is extended to that of semi-supervised learning (ss-learning), in which a collection of disjoint concepts is to be simultaneously learned with only partial information concerning concept membership available to the learning algorithm.
Raymond Board, Leonard Pitt
openaire +3 more sources
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input.
Takeru Miyato +3 more
semanticscholar +1 more source
A survey of large-scale graph-based semi-supervised classification algorithms
International Journal of Cognitive Computing in Engineering, 2022 Semi-supervised learning is an effective method to study how to use both labeled data and unlabeled data to improve the performance of the classifier, which has become the hot field of machine learning in recent years.
Yunsheng Song, Jing Zhang, Chao Zhang
doaj +1 more source
Semi-supervised Learning Method Based on Automated Mixed Sample Data Augmentation Techniques [PDF]
Jisuanji kexue, 2022 Consistency-based semi-supervised learning methods typically use simple data augmentation methods to achieve consistent predictions for both original inputs and perturbed inputs.The effectiveness of this approach is difficult to be guaranteed when the ...
XU Hua-jie, CHEN Yu, YANG Yang, QIN Yuan-zhuo
doaj +1 more source
Learning to Learn in a Semi-supervised Fashion [PDF]
, 2020 To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like in person re-identification or image retrieval.
Chao-Te Chou +2 more
openaire +3 more sources
Contrastive Semi-Supervised Learning for ASR [PDF]
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021 Pseudo-labeling is the most adopted method for pre-training automatic speech recognition (ASR) models. However, its performance suffers from the supervised teacher model's degrading quality in low-resource setups and under domain transfer. Inspired by the successes of contrastive representation learning for computer vision and speech applications, and ...
Christian Fuegen +2 more
openaire +3 more sources
ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning [PDF]
IEEE Workshop/Winter Conference on Applications of Computer Vision, 2020 The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications.
Viktor Olsson +3 more
semanticscholar +1 more source
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization [PDF]
IEEE International Conference on Computer Vision, 2020 Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their limitations ...
Junnan Li, Caiming Xiong, S. Hoi
semanticscholar +1 more source
Meta-Semi: A Meta-Learning Approach for Semi-Supervised Learning
CAAI Artificial Intelligence Research, 2022 Deep learning based semi-supervised learning (SSL) algorithms have led to promising results in recent years. However, they tend to introduce multiple tunable hyper-parameters, making them less practical in real SSL scenarios where the labeled data is ...
Yulin Wang +5 more
doaj +1 more source