Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313304796> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4313304796 abstract "Self-supervised learning is a popular and powerful method for utilizing large amounts of unlabeled data, for which a wide variety of training objectives have been proposed in the literature. In this study, we perform a Bayesian analysis of state-of-the-art self-supervised learning objectives and propose a unified formulation based on likelihood learning. Our analysis suggests a simple method for integrating self-supervised learning with generative models, allowing for the joint training of these two seemingly distinct approaches. We refer to this combined framework as GEDI, which stands for GEnerative and DIscriminative training. Additionally, we demonstrate an instantiation of the GEDI framework by integrating an energy-based model with a cluster-based self-supervised learning model. Through experiments on synthetic and real-world data, including SVHN, CIFAR10, and CIFAR100, we show that GEDI outperforms existing self-supervised learning strategies in terms of clustering performance by a wide margin. We also demonstrate that GEDI can be integrated into a neural-symbolic framework to address tasks in the small data regime, where it can use logical constraints to further improve clustering and classification performance." @default.
- W4313304796 created "2023-01-06" @default.
- W4313304796 creator A5003576783 @default.
- W4313304796 creator A5089739736 @default.
- W4313304796 date "2022-12-27" @default.
- W4313304796 modified "2023-09-23" @default.
- W4313304796 title "GEDI: GEnerative and DIscriminative Training for Self-Supervised Learning" @default.
- W4313304796 doi "https://doi.org/10.48550/arxiv.2212.13425" @default.
- W4313304796 hasPublicationYear "2022" @default.
- W4313304796 type Work @default.
- W4313304796 citedByCount "0" @default.
- W4313304796 crossrefType "posted-content" @default.
- W4313304796 hasAuthorship W4313304796A5003576783 @default.
- W4313304796 hasAuthorship W4313304796A5089739736 @default.
- W4313304796 hasBestOaLocation W43133047961 @default.
- W4313304796 hasConcept C107673813 @default.
- W4313304796 hasConcept C119857082 @default.
- W4313304796 hasConcept C136197465 @default.
- W4313304796 hasConcept C136389625 @default.
- W4313304796 hasConcept C154945302 @default.
- W4313304796 hasConcept C167966045 @default.
- W4313304796 hasConcept C39890363 @default.
- W4313304796 hasConcept C41008148 @default.
- W4313304796 hasConcept C50644808 @default.
- W4313304796 hasConcept C58973888 @default.
- W4313304796 hasConcept C73555534 @default.
- W4313304796 hasConcept C774472 @default.
- W4313304796 hasConcept C97931131 @default.
- W4313304796 hasConceptScore W4313304796C107673813 @default.
- W4313304796 hasConceptScore W4313304796C119857082 @default.
- W4313304796 hasConceptScore W4313304796C136197465 @default.
- W4313304796 hasConceptScore W4313304796C136389625 @default.
- W4313304796 hasConceptScore W4313304796C154945302 @default.
- W4313304796 hasConceptScore W4313304796C167966045 @default.
- W4313304796 hasConceptScore W4313304796C39890363 @default.
- W4313304796 hasConceptScore W4313304796C41008148 @default.
- W4313304796 hasConceptScore W4313304796C50644808 @default.
- W4313304796 hasConceptScore W4313304796C58973888 @default.
- W4313304796 hasConceptScore W4313304796C73555534 @default.
- W4313304796 hasConceptScore W4313304796C774472 @default.
- W4313304796 hasConceptScore W4313304796C97931131 @default.
- W4313304796 hasLocation W43133047961 @default.
- W4313304796 hasOpenAccess W4313304796 @default.
- W4313304796 hasPrimaryLocation W43133047961 @default.
- W4313304796 hasRelatedWork W1534961803 @default.
- W4313304796 hasRelatedWork W2095758845 @default.
- W4313304796 hasRelatedWork W2104755048 @default.
- W4313304796 hasRelatedWork W2551446786 @default.
- W4313304796 hasRelatedWork W2896015807 @default.
- W4313304796 hasRelatedWork W2951996801 @default.
- W4313304796 hasRelatedWork W2964274470 @default.
- W4313304796 hasRelatedWork W2987786433 @default.
- W4313304796 hasRelatedWork W4297816859 @default.
- W4313304796 hasRelatedWork W2310403681 @default.
- W4313304796 isParatext "false" @default.
- W4313304796 isRetracted "false" @default.
- W4313304796 workType "article" @default.