Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386879750> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4386879750 endingPage "e01903" @default.
- W4386879750 startingPage "e01903" @default.
- W4386879750 abstract "This study investigates the relationship between semi-supervised learning (SSL, which is training off partially labelled datasets) and open-set recognition (OSR, which is classification with simultaneous novelty detection) under the context of generative adversarial networks (GANs). Although no previous study has formally linked SSL and OSR, their respective methods share striking similarities. Specifically, SSL-GANs and OSR-GANs require their generators to produce ’bad-looking’ samples which are used to regularise their classifier networks. We hypothesise that the definitions of bad-looking samples in SSL and OSR represents the same concept and realises the same goal. More formally, bad-looking samples lie in the complementary space, which is the area between and around the boundaries of the labelled categories within the classifier’s embedding space. By regularising a classifier with samples in the complementary space, classifiers achieve improved generalisation for SSL and also generalise the open space for OSR. To test this hypothesis, we compare a foundational SSL-GAN with the state-of-the-art OSR-GAN under the same SSL-OSR experimental conditions. Our results find that SSL-GANs achieve near identical results to OSR-GANs, proving the SSL-OSR link. Subsequently, to further this new research path, we compare several SSL-GANs various SSL-OSR setups which this first benchmark results. A combined framework of SSL-OSR certainly improves the practicality and cost-efficiency of classifier training, and so further theoretical and application studies are also discussed." @default.
- W4386879750 created "2023-09-21" @default.
- W4386879750 creator A5028807248 @default.
- W4386879750 creator A5055347392 @default.
- W4386879750 date "2023-11-01" @default.
- W4386879750 modified "2023-10-16" @default.
- W4386879750 title "On the link between generative semi-supervised learning and generative open-set recognition" @default.
- W4386879750 cites W2115627867 @default.
- W4386879750 cites W2911988840 @default.
- W4386879750 cites W2963049059 @default.
- W4386879750 cites W2963061824 @default.
- W4386879750 cites W2984353870 @default.
- W4386879750 cites W3010462080 @default.
- W4386879750 cites W3010977049 @default.
- W4386879750 cites W3011127849 @default.
- W4386879750 cites W3042783488 @default.
- W4386879750 cites W3042964830 @default.
- W4386879750 cites W3086580107 @default.
- W4386879750 cites W3102615300 @default.
- W4386879750 cites W3111818226 @default.
- W4386879750 cites W3113374047 @default.
- W4386879750 cites W3134961575 @default.
- W4386879750 cites W3158023256 @default.
- W4386879750 cites W3177009355 @default.
- W4386879750 cites W3207167009 @default.
- W4386879750 cites W4205646447 @default.
- W4386879750 cites W4229067108 @default.
- W4386879750 cites W4308582138 @default.
- W4386879750 cites W4311804469 @default.
- W4386879750 cites W4320150074 @default.
- W4386879750 doi "https://doi.org/10.1016/j.sciaf.2023.e01903" @default.
- W4386879750 hasPublicationYear "2023" @default.
- W4386879750 type Work @default.
- W4386879750 citedByCount "0" @default.
- W4386879750 crossrefType "journal-article" @default.
- W4386879750 hasAuthorship W4386879750A5028807248 @default.
- W4386879750 hasAuthorship W4386879750A5055347392 @default.
- W4386879750 hasBestOaLocation W43868797501 @default.
- W4386879750 hasConcept C118615104 @default.
- W4386879750 hasConcept C119857082 @default.
- W4386879750 hasConcept C153180895 @default.
- W4386879750 hasConcept C154945302 @default.
- W4386879750 hasConcept C33923547 @default.
- W4386879750 hasConcept C39890363 @default.
- W4386879750 hasConcept C41008148 @default.
- W4386879750 hasConcept C42357961 @default.
- W4386879750 hasConcept C95623464 @default.
- W4386879750 hasConceptScore W4386879750C118615104 @default.
- W4386879750 hasConceptScore W4386879750C119857082 @default.
- W4386879750 hasConceptScore W4386879750C153180895 @default.
- W4386879750 hasConceptScore W4386879750C154945302 @default.
- W4386879750 hasConceptScore W4386879750C33923547 @default.
- W4386879750 hasConceptScore W4386879750C39890363 @default.
- W4386879750 hasConceptScore W4386879750C41008148 @default.
- W4386879750 hasConceptScore W4386879750C42357961 @default.
- W4386879750 hasConceptScore W4386879750C95623464 @default.
- W4386879750 hasLocation W43868797501 @default.
- W4386879750 hasOpenAccess W4386879750 @default.
- W4386879750 hasPrimaryLocation W43868797501 @default.
- W4386879750 hasRelatedWork W1576360539 @default.
- W4386879750 hasRelatedWork W2167582322 @default.
- W4386879750 hasRelatedWork W2556319748 @default.
- W4386879750 hasRelatedWork W2563096758 @default.
- W4386879750 hasRelatedWork W2742991909 @default.
- W4386879750 hasRelatedWork W2961085424 @default.
- W4386879750 hasRelatedWork W2972035100 @default.
- W4386879750 hasRelatedWork W3092365268 @default.
- W4386879750 hasRelatedWork W4386053843 @default.
- W4386879750 hasRelatedWork W3158004940 @default.
- W4386879750 hasVolume "22" @default.
- W4386879750 isParatext "false" @default.
- W4386879750 isRetracted "false" @default.
- W4386879750 workType "article" @default.