Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318766189> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4318766189 endingPage "14" @default.
- W4318766189 startingPage "1" @default.
- W4318766189 abstract "Semi-supervised learning is a common way that investigates how to improve performance of a visual learning model, while data annotation is far from sufficient. Recent works in semi-supervised deep learning have successfully applied consistency regularization, which encourages a model to maintain consistent predictions for different perturbed versions of an image. However, most of such methods ignore the category correlation of image features, especially when exploiting strong augmentation methods for unlabeled images. To address this problem, we propose PConMatch, a model that leverages a probabilistic contrastive learning framework to separate the features of strongly-augmented versions from different classes. A semi-supervised probabilistic contrastive loss is designed, which takes both labeled and unlabeled samples into account and develops an auxiliary module to generate a probability score to measure the model prediction confidence for each sample. Specifically, PConMatch first generates a pair of weakly-augmented versions for each labeled sample, and produces a weakly-augmented version and a corresponding pair of strongly-augmented versions for each unlabeled sample. Second, a probability score module is proposed to assign pseudo-labeling confidence scores to strongly-augmented unlabeled images. Finally, the probability score of each sample is further passed to the contrastive loss, combining with consistency regularization to enable the model to learn better feature representations. Extensive experiments on four publicly available image classification benchmarks demonstrate that the proposed approach achieves state-of-the-art performance in image classification. Several rigorous ablation studies are conducted to validate the effectiveness of the method." @default.
- W4318766189 created "2023-02-02" @default.
- W4318766189 creator A5002405830 @default.
- W4318766189 creator A5021852079 @default.
- W4318766189 creator A5036978677 @default.
- W4318766189 creator A5085340418 @default.
- W4318766189 date "2023-01-01" @default.
- W4318766189 modified "2023-10-14" @default.
- W4318766189 title "A Probabilistic Contrastive Framework for Semi-Supervised Learning" @default.
- W4318766189 doi "https://doi.org/10.1109/tmm.2023.3241539" @default.
- W4318766189 hasPublicationYear "2023" @default.
- W4318766189 type Work @default.
- W4318766189 citedByCount "0" @default.
- W4318766189 crossrefType "journal-article" @default.
- W4318766189 hasAuthorship W4318766189A5002405830 @default.
- W4318766189 hasAuthorship W4318766189A5021852079 @default.
- W4318766189 hasAuthorship W4318766189A5036978677 @default.
- W4318766189 hasAuthorship W4318766189A5085340418 @default.
- W4318766189 hasConcept C114289077 @default.
- W4318766189 hasConcept C119857082 @default.
- W4318766189 hasConcept C138885662 @default.
- W4318766189 hasConcept C153180895 @default.
- W4318766189 hasConcept C154945302 @default.
- W4318766189 hasConcept C2776135515 @default.
- W4318766189 hasConcept C2776401178 @default.
- W4318766189 hasConcept C2776436953 @default.
- W4318766189 hasConcept C41008148 @default.
- W4318766189 hasConcept C41895202 @default.
- W4318766189 hasConcept C49937458 @default.
- W4318766189 hasConcept C58973888 @default.
- W4318766189 hasConceptScore W4318766189C114289077 @default.
- W4318766189 hasConceptScore W4318766189C119857082 @default.
- W4318766189 hasConceptScore W4318766189C138885662 @default.
- W4318766189 hasConceptScore W4318766189C153180895 @default.
- W4318766189 hasConceptScore W4318766189C154945302 @default.
- W4318766189 hasConceptScore W4318766189C2776135515 @default.
- W4318766189 hasConceptScore W4318766189C2776401178 @default.
- W4318766189 hasConceptScore W4318766189C2776436953 @default.
- W4318766189 hasConceptScore W4318766189C41008148 @default.
- W4318766189 hasConceptScore W4318766189C41895202 @default.
- W4318766189 hasConceptScore W4318766189C49937458 @default.
- W4318766189 hasConceptScore W4318766189C58973888 @default.
- W4318766189 hasFunder F4320321001 @default.
- W4318766189 hasFunder F4320321878 @default.
- W4318766189 hasLocation W43187661891 @default.
- W4318766189 hasOpenAccess W4318766189 @default.
- W4318766189 hasPrimaryLocation W43187661891 @default.
- W4318766189 hasRelatedWork W2016461833 @default.
- W4318766189 hasRelatedWork W2052253960 @default.
- W4318766189 hasRelatedWork W2147802381 @default.
- W4318766189 hasRelatedWork W2295628041 @default.
- W4318766189 hasRelatedWork W2382607599 @default.
- W4318766189 hasRelatedWork W2546942002 @default.
- W4318766189 hasRelatedWork W2760085659 @default.
- W4318766189 hasRelatedWork W2929240682 @default.
- W4318766189 hasRelatedWork W3025582806 @default.
- W4318766189 hasRelatedWork W3210156800 @default.
- W4318766189 isParatext "false" @default.
- W4318766189 isRetracted "false" @default.
- W4318766189 workType "article" @default.