Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387552216> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4387552216 endingPage "105536" @default.
- W4387552216 startingPage "105536" @default.
- W4387552216 abstract "The crux of medical image segmentation stems from learning pixel-wise semantic consistency from a mount of labeled samples through exhaustive annotation. Most existing methods rely heavily on labeled image pairs and are optimized in a fully supervised manner, often resulting in unsatisfactory results due to limited paired training samples. In this paper, we propose a GAN inversion-based semi-supervised learning framework InvSSL for medical image segmentation, which generates corresponding variants from labeled images by GAN inversion. Specifically, it first trains a StyleGAN as an inversion generator which is able to generate samples with the same distribution as training samples, and then obtains variant samples from a training sample by performing GAN inversion to strengthen the segmentation performance in a semi-supervised learning manner. In particular, inversion generator inverts a training sample into the latent space and adds interference to the latent codes to evolve variant samples. To model high-level consistency between pixels and decouple semantic components in the latent space, our InvSSL designs a multi-level dense contrastive learning mechanism. Extensive experiments on lung segmentation and skin lesion segmentation demonstrate that our InvSSL outperforms state-of-the-art methods for medical image segmentation. Our code will be released at https://github.com/funkdub/InvSSL." @default.
- W4387552216 created "2023-10-12" @default.
- W4387552216 creator A5019972814 @default.
- W4387552216 creator A5044044031 @default.
- W4387552216 creator A5049444898 @default.
- W4387552216 creator A5064349528 @default.
- W4387552216 date "2024-02-01" @default.
- W4387552216 modified "2023-10-12" @default.
- W4387552216 title "GAN inversion-based semi-supervised learning for medical image segmentation" @default.
- W4387552216 cites W1903029394 @default.
- W4387552216 cites W1909740415 @default.
- W4387552216 cites W1994062553 @default.
- W4387552216 cites W2024798729 @default.
- W4387552216 cites W2142514727 @default.
- W4387552216 cites W2412782625 @default.
- W4387552216 cites W2732931556 @default.
- W4387552216 cites W2763160469 @default.
- W4387552216 cites W2774320778 @default.
- W4387552216 cites W2962770929 @default.
- W4387552216 cites W2962825119 @default.
- W4387552216 cites W2963797156 @default.
- W4387552216 cites W2963881378 @default.
- W4387552216 cites W2996290406 @default.
- W4387552216 cites W3021980948 @default.
- W4387552216 cites W3025800305 @default.
- W4387552216 cites W3034431451 @default.
- W4387552216 cites W3035524453 @default.
- W4387552216 cites W3035574324 @default.
- W4387552216 cites W3083779147 @default.
- W4387552216 cites W3101156210 @default.
- W4387552216 cites W3102785203 @default.
- W4387552216 cites W3118974483 @default.
- W4387552216 cites W3156786744 @default.
- W4387552216 cites W3168822201 @default.
- W4387552216 cites W3173143063 @default.
- W4387552216 cites W3202296139 @default.
- W4387552216 cites W343636949 @default.
- W4387552216 cites W4214762187 @default.
- W4387552216 cites W4224215706 @default.
- W4387552216 cites W4232097126 @default.
- W4387552216 cites W4287448984 @default.
- W4387552216 cites W4294862191 @default.
- W4387552216 cites W4294982666 @default.
- W4387552216 cites W4296901926 @default.
- W4387552216 cites W4312443924 @default.
- W4387552216 cites W4313479430 @default.
- W4387552216 doi "https://doi.org/10.1016/j.bspc.2023.105536" @default.
- W4387552216 hasPublicationYear "2024" @default.
- W4387552216 type Work @default.
- W4387552216 citedByCount "0" @default.
- W4387552216 crossrefType "journal-article" @default.
- W4387552216 hasAuthorship W4387552216A5019972814 @default.
- W4387552216 hasAuthorship W4387552216A5044044031 @default.
- W4387552216 hasAuthorship W4387552216A5049444898 @default.
- W4387552216 hasAuthorship W4387552216A5064349528 @default.
- W4387552216 hasConcept C109007969 @default.
- W4387552216 hasConcept C124504099 @default.
- W4387552216 hasConcept C151730666 @default.
- W4387552216 hasConcept C153180895 @default.
- W4387552216 hasConcept C154945302 @default.
- W4387552216 hasConcept C160633673 @default.
- W4387552216 hasConcept C1893757 @default.
- W4387552216 hasConcept C2776321320 @default.
- W4387552216 hasConcept C31972630 @default.
- W4387552216 hasConcept C41008148 @default.
- W4387552216 hasConcept C65885262 @default.
- W4387552216 hasConcept C86803240 @default.
- W4387552216 hasConcept C89600930 @default.
- W4387552216 hasConceptScore W4387552216C109007969 @default.
- W4387552216 hasConceptScore W4387552216C124504099 @default.
- W4387552216 hasConceptScore W4387552216C151730666 @default.
- W4387552216 hasConceptScore W4387552216C153180895 @default.
- W4387552216 hasConceptScore W4387552216C154945302 @default.
- W4387552216 hasConceptScore W4387552216C160633673 @default.
- W4387552216 hasConceptScore W4387552216C1893757 @default.
- W4387552216 hasConceptScore W4387552216C2776321320 @default.
- W4387552216 hasConceptScore W4387552216C31972630 @default.
- W4387552216 hasConceptScore W4387552216C41008148 @default.
- W4387552216 hasConceptScore W4387552216C65885262 @default.
- W4387552216 hasConceptScore W4387552216C86803240 @default.
- W4387552216 hasConceptScore W4387552216C89600930 @default.
- W4387552216 hasLocation W43875522161 @default.
- W4387552216 hasOpenAccess W4387552216 @default.
- W4387552216 hasPrimaryLocation W43875522161 @default.
- W4387552216 hasRelatedWork W1999008862 @default.
- W4387552216 hasRelatedWork W2022929107 @default.
- W4387552216 hasRelatedWork W2103507220 @default.
- W4387552216 hasRelatedWork W2185902295 @default.
- W4387552216 hasRelatedWork W2386644571 @default.
- W4387552216 hasRelatedWork W2945274617 @default.
- W4387552216 hasRelatedWork W3144569342 @default.
- W4387552216 hasRelatedWork W4205800335 @default.
- W4387552216 hasRelatedWork W4313052709 @default.
- W4387552216 hasRelatedWork W80586315 @default.
- W4387552216 hasVolume "88" @default.
- W4387552216 isParatext "false" @default.
- W4387552216 isRetracted "false" @default.
- W4387552216 workType "article" @default.