FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3181871665> ?p ?o ?g. }

• W3181871665 abstract "The goal is to use Wasserstein metric to provide pseudo labels for the unlabeled images to train a Convolutional Neural Networks (CNN) in a Semi-Supervised Learning (SSL) manner for the classification task. The basic premise in our method is that the discrepancy between two discrete empirical measures (e.g., clusters) which come from the same or similar distribution is expected to be less than the case where these measures come from completely two different distributions. In our proposed method, we first pre-train our CNN using a self-supervised learning method to make a cluster assumption on the unlabeled images. Next, inspired by the Wasserstein metric which considers the geometry of the metric space to provide a natural notion of similarity between discrete empirical measures, we leverage it to cluster the unlabeled images and then match the clusters to their similar class of labeled images to provide a pseudo label for the data within each cluster. We have evaluated and compared our method with state-of-the-art SSL methods on the standard datasets to demonstrate its effectiveness." @default.
• W3181871665 created "2021-07-19" @default.
• W3181871665 creator A5021852735 @default.
• W3181871665 creator A5043534833 @default.
• W3181871665 creator A5068143389 @default.
• W3181871665 creator A5076900687 @default.
• W3181871665 creator A5084719864 @default.
• W3181871665 date "2021-06-01" @default.
• W3181871665 modified "2023-10-09" @default.
• W3181871665 title "Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification" @default.
• W3181871665 cites W1594039573 @default.
• W3181871665 cites W1968333723 @default.
• W3181871665 cites W1983320747 @default.
• W3181871665 cites W2060640288 @default.
• W3181871665 cites W2108598243 @default.
• W3181871665 cites W2298250094 @default.
• W3181871665 cites W2735418187 @default.
• W3181871665 cites W2798991696 @default.
• W3181871665 cites W2800292742 @default.
• W3181871665 cites W2808408933 @default.
• W3181871665 cites W2809829633 @default.
• W3181871665 cites W2914913933 @default.
• W3181871665 cites W2962697512 @default.
• W3181871665 cites W2962723373 @default.
• W3181871665 cites W2963187488 @default.
• W3181871665 cites W2963558289 @default.
• W3181871665 cites W2963995333 @default.
• W3181871665 cites W2964137095 @default.
• W3181871665 cites W2964334477 @default.
• W3181871665 cites W2979744195 @default.
• W3181871665 cites W2979805229 @default.
• W3181871665 cites W2980096013 @default.
• W3181871665 cites W2982376094 @default.
• W3181871665 cites W2997131443 @default.
• W3181871665 cites W3023534255 @default.
• W3181871665 cites W3035524453 @default.
• W3181871665 cites W3035682985 @default.
• W3181871665 cites W3037876595 @default.
• W3181871665 cites W3091002423 @default.
• W3181871665 cites W3096461453 @default.
• W3181871665 cites W4254182148 @default.
• W3181871665 cites W4255839052 @default.
• W3181871665 doi "https://doi.org/10.1109/cvpr46437.2021.01209" @default.
• W3181871665 hasPublicationYear "2021" @default.
• W3181871665 type Work @default.
• W3181871665 sameAs 3181871665 @default.
• W3181871665 citedByCount "15" @default.
• W3181871665 countsByYear W31818716652022 @default.
• W3181871665 countsByYear W31818716652023 @default.
• W3181871665 crossrefType "proceedings-article" @default.
• W3181871665 hasAuthorship W3181871665A5021852735 @default.
• W3181871665 hasAuthorship W3181871665A5043534833 @default.
• W3181871665 hasAuthorship W3181871665A5068143389 @default.
• W3181871665 hasAuthorship W3181871665A5076900687 @default.
• W3181871665 hasAuthorship W3181871665A5084719864 @default.
• W3181871665 hasConcept C103278499 @default.
• W3181871665 hasConcept C115961682 @default.
• W3181871665 hasConcept C119857082 @default.
• W3181871665 hasConcept C136389625 @default.
• W3181871665 hasConcept C153083717 @default.
• W3181871665 hasConcept C153180895 @default.
• W3181871665 hasConcept C154945302 @default.
• W3181871665 hasConcept C162324750 @default.
• W3181871665 hasConcept C176217482 @default.
• W3181871665 hasConcept C21547014 @default.
• W3181871665 hasConcept C33923547 @default.
• W3181871665 hasConcept C41008148 @default.
• W3181871665 hasConcept C50644808 @default.
• W3181871665 hasConcept C58973888 @default.
• W3181871665 hasConcept C75294576 @default.
• W3181871665 hasConcept C81363708 @default.
• W3181871665 hasConceptScore W3181871665C103278499 @default.
• W3181871665 hasConceptScore W3181871665C115961682 @default.
• W3181871665 hasConceptScore W3181871665C119857082 @default.
• W3181871665 hasConceptScore W3181871665C136389625 @default.
• W3181871665 hasConceptScore W3181871665C153083717 @default.
• W3181871665 hasConceptScore W3181871665C153180895 @default.
• W3181871665 hasConceptScore W3181871665C154945302 @default.
• W3181871665 hasConceptScore W3181871665C162324750 @default.
• W3181871665 hasConceptScore W3181871665C176217482 @default.
• W3181871665 hasConceptScore W3181871665C21547014 @default.
• W3181871665 hasConceptScore W3181871665C33923547 @default.
• W3181871665 hasConceptScore W3181871665C41008148 @default.
• W3181871665 hasConceptScore W3181871665C50644808 @default.
• W3181871665 hasConceptScore W3181871665C58973888 @default.
• W3181871665 hasConceptScore W3181871665C75294576 @default.
• W3181871665 hasConceptScore W3181871665C81363708 @default.
• W3181871665 hasLocation W31818716651 @default.
• W3181871665 hasOpenAccess W3181871665 @default.
• W3181871665 hasPrimaryLocation W31818716651 @default.
• W3181871665 hasRelatedWork W2767651786 @default.
• W3181871665 hasRelatedWork W2912288872 @default.
• W3181871665 hasRelatedWork W3094076422 @default.
• W3181871665 hasRelatedWork W3143586484 @default.
• W3181871665 hasRelatedWork W3162567751 @default.
• W3181871665 hasRelatedWork W4285260836 @default.
• W3181871665 hasRelatedWork W4287237811 @default.
• W3181871665 hasRelatedWork W4312992234 @default.
• W3181871665 hasRelatedWork W4319309271 @default.
• W3181871665 hasRelatedWork W4361193208 @default.

• next