Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200469221> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4200469221 abstract "Self-supervised learning approaches were shown to benefit feature learning by training models under a pretext task. In this context, learning from limited data can be tackled using a combination of semi-supervised learning and self-supervision. In this paper we combine the traditional supervised learning paradigm with the rotation prediction self-supervised task, that are used simultaneously to train a siamese model with a joint loss function and shared weights. In particular, we are interested in the case in which the proportion of labeled with respect to unlabeled data is small. We investigate the effectiveness of a compact feature space obtained after training under such limited annotation scenario, in terms of linear class separability and under attack. The study includes images from multiple domains, such as natural images (STL-10 dataset), products (Fashion-MNIST dataset) and biomedical images (Malaria dataset). We show that in scenarios where we have only a few labeled data the model augmented with a self-supervised task can take advantage of the unlabeled data to improve the learned representation in terms of the linear discrimination, as well as allowing learning even under attack. Also, we discuss the choices in terms of self-supervision and cases of failure considering the different datasets." @default.
- W4200469221 created "2021-12-31" @default.
- W4200469221 creator A5029845097 @default.
- W4200469221 creator A5086605553 @default.
- W4200469221 date "2021-10-01" @default.
- W4200469221 modified "2023-09-26" @default.
- W4200469221 title "Semi-supervised siamese network using self-supervision under scarce annotation improves class separability and robustness to attack" @default.
- W4200469221 doi "https://doi.org/10.1109/sibgrapi54419.2021.00038" @default.
- W4200469221 hasPublicationYear "2021" @default.
- W4200469221 type Work @default.
- W4200469221 citedByCount "0" @default.
- W4200469221 crossrefType "proceedings-article" @default.
- W4200469221 hasAuthorship W4200469221A5029845097 @default.
- W4200469221 hasAuthorship W4200469221A5086605553 @default.
- W4200469221 hasConcept C104317684 @default.
- W4200469221 hasConcept C108583219 @default.
- W4200469221 hasConcept C119857082 @default.
- W4200469221 hasConcept C136389625 @default.
- W4200469221 hasConcept C151730666 @default.
- W4200469221 hasConcept C153180895 @default.
- W4200469221 hasConcept C154945302 @default.
- W4200469221 hasConcept C162324750 @default.
- W4200469221 hasConcept C185592680 @default.
- W4200469221 hasConcept C187736073 @default.
- W4200469221 hasConcept C190502265 @default.
- W4200469221 hasConcept C2776145971 @default.
- W4200469221 hasConcept C2776321320 @default.
- W4200469221 hasConcept C2777212361 @default.
- W4200469221 hasConcept C2779343474 @default.
- W4200469221 hasConcept C2780451532 @default.
- W4200469221 hasConcept C41008148 @default.
- W4200469221 hasConcept C50644808 @default.
- W4200469221 hasConcept C55493867 @default.
- W4200469221 hasConcept C58973888 @default.
- W4200469221 hasConcept C59404180 @default.
- W4200469221 hasConcept C63479239 @default.
- W4200469221 hasConcept C83665646 @default.
- W4200469221 hasConcept C86803240 @default.
- W4200469221 hasConceptScore W4200469221C104317684 @default.
- W4200469221 hasConceptScore W4200469221C108583219 @default.
- W4200469221 hasConceptScore W4200469221C119857082 @default.
- W4200469221 hasConceptScore W4200469221C136389625 @default.
- W4200469221 hasConceptScore W4200469221C151730666 @default.
- W4200469221 hasConceptScore W4200469221C153180895 @default.
- W4200469221 hasConceptScore W4200469221C154945302 @default.
- W4200469221 hasConceptScore W4200469221C162324750 @default.
- W4200469221 hasConceptScore W4200469221C185592680 @default.
- W4200469221 hasConceptScore W4200469221C187736073 @default.
- W4200469221 hasConceptScore W4200469221C190502265 @default.
- W4200469221 hasConceptScore W4200469221C2776145971 @default.
- W4200469221 hasConceptScore W4200469221C2776321320 @default.
- W4200469221 hasConceptScore W4200469221C2777212361 @default.
- W4200469221 hasConceptScore W4200469221C2779343474 @default.
- W4200469221 hasConceptScore W4200469221C2780451532 @default.
- W4200469221 hasConceptScore W4200469221C41008148 @default.
- W4200469221 hasConceptScore W4200469221C50644808 @default.
- W4200469221 hasConceptScore W4200469221C55493867 @default.
- W4200469221 hasConceptScore W4200469221C58973888 @default.
- W4200469221 hasConceptScore W4200469221C59404180 @default.
- W4200469221 hasConceptScore W4200469221C63479239 @default.
- W4200469221 hasConceptScore W4200469221C83665646 @default.
- W4200469221 hasConceptScore W4200469221C86803240 @default.
- W4200469221 hasLocation W42004692211 @default.
- W4200469221 hasOpenAccess W4200469221 @default.
- W4200469221 hasPrimaryLocation W42004692211 @default.
- W4200469221 hasRelatedWork W10885063 @default.
- W4200469221 hasRelatedWork W10980763 @default.
- W4200469221 hasRelatedWork W11738893 @default.
- W4200469221 hasRelatedWork W1655064 @default.
- W4200469221 hasRelatedWork W4972971 @default.
- W4200469221 hasRelatedWork W5236451 @default.
- W4200469221 hasRelatedWork W6310906 @default.
- W4200469221 hasRelatedWork W8198582 @default.
- W4200469221 hasRelatedWork W8248617 @default.
- W4200469221 hasRelatedWork W9480776 @default.
- W4200469221 isParatext "false" @default.
- W4200469221 isRetracted "false" @default.
- W4200469221 workType "article" @default.