Matches in SemOpenAlex for { <https://semopenalex.org/work/W2751127531> ?p ?o ?g. }
- W2751127531 abstract "We propose introspective convolutional networks (ICN) that emphasize the importance of having convolutional neural networks empowered with generative capabilities. We employ a reclassification-by-synthesis algorithm to perform training using a formulation stemmed from the Bayes theory. Our ICN tries to iteratively: (1) synthesize pseudo-negative samples; and (2) enhance itself by improving the classification. The single CNN classifier learned is at the same time generative --- being able to directly synthesize new samples within its own discriminative model. We conduct experiments on benchmark datasets including MNIST, CIFAR-10, and SVHN using state-of-the-art CNN architectures, and observe improved classification results." @default.
- W2751127531 created "2017-09-15" @default.
- W2751127531 creator A5001760915 @default.
- W2751127531 creator A5050729402 @default.
- W2751127531 creator A5088583935 @default.
- W2751127531 date "2017-04-25" @default.
- W2751127531 modified "2023-09-26" @default.
- W2751127531 title "Introspective Classification with Convolutional Nets" @default.
- W2751127531 cites W1555683961 @default.
- W2751127531 cites W1556724575 @default.
- W2751127531 cites W1833977909 @default.
- W2751127531 cites W1924619199 @default.
- W2751127531 cites W1993845689 @default.
- W2751127531 cites W2099471712 @default.
- W2751127531 cites W2103504567 @default.
- W2751127531 cites W2107958340 @default.
- W2751127531 cites W2110119381 @default.
- W2751127531 cites W2126043693 @default.
- W2751127531 cites W2126174118 @default.
- W2751127531 cites W2136504847 @default.
- W2751127531 cites W2136922672 @default.
- W2751127531 cites W2147800946 @default.
- W2751127531 cites W2152790380 @default.
- W2751127531 cites W2156346614 @default.
- W2751127531 cites W2156909104 @default.
- W2751127531 cites W2163176424 @default.
- W2751127531 cites W2167433878 @default.
- W2751127531 cites W2167595980 @default.
- W2751127531 cites W2181347294 @default.
- W2751127531 cites W2183341477 @default.
- W2751127531 cites W2194775991 @default.
- W2751127531 cites W2302255633 @default.
- W2751127531 cites W2432004435 @default.
- W2751127531 cites W2521028896 @default.
- W2751127531 cites W2605488176 @default.
- W2751127531 cites W2780786077 @default.
- W2751127531 cites W2903158431 @default.
- W2751127531 cites W2911964244 @default.
- W2751127531 cites W2949457404 @default.
- W2751127531 cites W2951105989 @default.
- W2751127531 cites W2952533959 @default.
- W2751127531 cites W2952943736 @default.
- W2751127531 cites W2963207607 @default.
- W2751127531 cites W2963606038 @default.
- W2751127531 cites W2963684088 @default.
- W2751127531 cites W2963919294 @default.
- W2751127531 cites W2964121744 @default.
- W2751127531 cites W2964144352 @default.
- W2751127531 cites W2987280934 @default.
- W2751127531 cites W3118608800 @default.
- W2751127531 cites W66838807 @default.
- W2751127531 doi "https://doi.org/10.48550/arxiv.1704.07816" @default.
- W2751127531 hasPublicationYear "2017" @default.
- W2751127531 type Work @default.
- W2751127531 sameAs 2751127531 @default.
- W2751127531 citedByCount "0" @default.
- W2751127531 crossrefType "posted-content" @default.
- W2751127531 hasAuthorship W2751127531A5001760915 @default.
- W2751127531 hasAuthorship W2751127531A5050729402 @default.
- W2751127531 hasAuthorship W2751127531A5088583935 @default.
- W2751127531 hasBestOaLocation W27511275311 @default.
- W2751127531 hasConcept C108583219 @default.
- W2751127531 hasConcept C119857082 @default.
- W2751127531 hasConcept C12267149 @default.
- W2751127531 hasConcept C129671850 @default.
- W2751127531 hasConcept C13280743 @default.
- W2751127531 hasConcept C153180895 @default.
- W2751127531 hasConcept C154945302 @default.
- W2751127531 hasConcept C15744967 @default.
- W2751127531 hasConcept C167966045 @default.
- W2751127531 hasConcept C180747234 @default.
- W2751127531 hasConcept C185798385 @default.
- W2751127531 hasConcept C190502265 @default.
- W2751127531 hasConcept C205649164 @default.
- W2751127531 hasConcept C39890363 @default.
- W2751127531 hasConcept C41008148 @default.
- W2751127531 hasConcept C52001869 @default.
- W2751127531 hasConcept C81363708 @default.
- W2751127531 hasConcept C95623464 @default.
- W2751127531 hasConcept C97931131 @default.
- W2751127531 hasConceptScore W2751127531C108583219 @default.
- W2751127531 hasConceptScore W2751127531C119857082 @default.
- W2751127531 hasConceptScore W2751127531C12267149 @default.
- W2751127531 hasConceptScore W2751127531C129671850 @default.
- W2751127531 hasConceptScore W2751127531C13280743 @default.
- W2751127531 hasConceptScore W2751127531C153180895 @default.
- W2751127531 hasConceptScore W2751127531C154945302 @default.
- W2751127531 hasConceptScore W2751127531C15744967 @default.
- W2751127531 hasConceptScore W2751127531C167966045 @default.
- W2751127531 hasConceptScore W2751127531C180747234 @default.
- W2751127531 hasConceptScore W2751127531C185798385 @default.
- W2751127531 hasConceptScore W2751127531C190502265 @default.
- W2751127531 hasConceptScore W2751127531C205649164 @default.
- W2751127531 hasConceptScore W2751127531C39890363 @default.
- W2751127531 hasConceptScore W2751127531C41008148 @default.
- W2751127531 hasConceptScore W2751127531C52001869 @default.
- W2751127531 hasConceptScore W2751127531C81363708 @default.
- W2751127531 hasConceptScore W2751127531C95623464 @default.
- W2751127531 hasConceptScore W2751127531C97931131 @default.
- W2751127531 hasLocation W27511275311 @default.