Matches in SemOpenAlex for { <https://semopenalex.org/work/W2801289723> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2801289723 abstract "Visual surface inspection is a challenging task due to the highly inconsistent appearance of the target surfaces and the abnormal regions. Most of the state-of-the-art methods are highly dependent on the labelled training samples, which are difficult to collect in practical industrial applications. To address this problem, we propose a generative adversarial network based framework for unsupervised surface inspection. The generative adversarial network is trained to generate the fake images analogous to the normal surface images. It implies that a well-trained GAN indeed learns a good representation of the normal surface images in a latent feature space. And consequently, the discriminator of GAN can serve as a naturally one-class classifier. We use the first three conventional layer of the discriminator as the feature extractor, whose response is sensitive to the abnormal regions. Particularly, a multi-scale fusion strategy is adopted to fuse the responses of the three convolution layers and thus improve the segmentation performance of abnormal detection. Various experimental results demonstrate the effectiveness of our proposed method." @default.
- W2801289723 created "2018-05-17" @default.
- W2801289723 creator A5004219448 @default.
- W2801289723 creator A5004299336 @default.
- W2801289723 creator A5046269668 @default.
- W2801289723 creator A5066334922 @default.
- W2801289723 date "2018-04-01" @default.
- W2801289723 modified "2023-09-30" @default.
- W2801289723 title "A Generative Adversarial Network Based Framework for Unsupervised Visual Surface Inspection" @default.
- W2801289723 cites W1988299413 @default.
- W2801289723 cites W1995875735 @default.
- W2801289723 cites W2072994056 @default.
- W2801289723 cites W2083974471 @default.
- W2801289723 cites W2121166252 @default.
- W2801289723 cites W2133059825 @default.
- W2801289723 cites W2133470515 @default.
- W2801289723 cites W2138046011 @default.
- W2801289723 cites W2194775991 @default.
- W2801289723 cites W2340896621 @default.
- W2801289723 cites W2395611524 @default.
- W2801289723 doi "https://doi.org/10.1109/icassp.2018.8462364" @default.
- W2801289723 hasPublicationYear "2018" @default.
- W2801289723 type Work @default.
- W2801289723 sameAs 2801289723 @default.
- W2801289723 citedByCount "14" @default.
- W2801289723 countsByYear W28012897232019 @default.
- W2801289723 countsByYear W28012897232020 @default.
- W2801289723 countsByYear W28012897232021 @default.
- W2801289723 countsByYear W28012897232022 @default.
- W2801289723 countsByYear W28012897232023 @default.
- W2801289723 crossrefType "proceedings-article" @default.
- W2801289723 hasAuthorship W2801289723A5004219448 @default.
- W2801289723 hasAuthorship W2801289723A5004299336 @default.
- W2801289723 hasAuthorship W2801289723A5046269668 @default.
- W2801289723 hasAuthorship W2801289723A5066334922 @default.
- W2801289723 hasConcept C108583219 @default.
- W2801289723 hasConcept C153180895 @default.
- W2801289723 hasConcept C154945302 @default.
- W2801289723 hasConcept C2988773926 @default.
- W2801289723 hasConcept C31972630 @default.
- W2801289723 hasConcept C37736160 @default.
- W2801289723 hasConcept C39890363 @default.
- W2801289723 hasConcept C41008148 @default.
- W2801289723 hasConcept C8038995 @default.
- W2801289723 hasConceptScore W2801289723C108583219 @default.
- W2801289723 hasConceptScore W2801289723C153180895 @default.
- W2801289723 hasConceptScore W2801289723C154945302 @default.
- W2801289723 hasConceptScore W2801289723C2988773926 @default.
- W2801289723 hasConceptScore W2801289723C31972630 @default.
- W2801289723 hasConceptScore W2801289723C37736160 @default.
- W2801289723 hasConceptScore W2801289723C39890363 @default.
- W2801289723 hasConceptScore W2801289723C41008148 @default.
- W2801289723 hasConceptScore W2801289723C8038995 @default.
- W2801289723 hasLocation W28012897231 @default.
- W2801289723 hasOpenAccess W2801289723 @default.
- W2801289723 hasPrimaryLocation W28012897231 @default.
- W2801289723 hasRelatedWork W2898421198 @default.
- W2801289723 hasRelatedWork W2901368259 @default.
- W2801289723 hasRelatedWork W2998996837 @default.
- W2801289723 hasRelatedWork W3024390022 @default.
- W2801289723 hasRelatedWork W3156291593 @default.
- W2801289723 hasRelatedWork W3164279787 @default.
- W2801289723 hasRelatedWork W4296176982 @default.
- W2801289723 hasRelatedWork W4311460979 @default.
- W2801289723 hasRelatedWork W4313479464 @default.
- W2801289723 hasRelatedWork W4316035501 @default.
- W2801289723 isParatext "false" @default.
- W2801289723 isRetracted "false" @default.
- W2801289723 magId "2801289723" @default.
- W2801289723 workType "article" @default.