Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300592870> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4300592870 abstract "Semantic segmentation based on deep learning methods can attain appealing accuracy provided large amounts of annotated samples. However, it remains a challenging task when only limited labelled data are available, which is especially common in medical imaging. In this paper, we propose to use Leaking GAN, a GAN-based semi-supervised architecture for retina vessel semantic segmentation. Our key idea is to pollute the discriminator by leaking information from the generator. This leads to more moderate generations that benefit the training of GAN. As a result, the unlabelled examples can be better utilized to boost the learning of the discriminator, which eventually leads to stronger classification performance. In addition, to overcome the variations in medical images, the mean-teacher mechanism is utilized as an auxiliary regularization of the discriminator. Further, we modify the focal loss to fit it as the consistency objective for mean-teacher regularizer. Extensive experiments demonstrate that the Leaking GAN framework achieves competitive performance compared to the state-of-the-art methods when evaluated on benchmark datasets including DRIVE, STARE and CHASE_DB1, using as few as 8 labelled images in the semi-supervised setting. It also outperforms existing algorithms on cross-domain segmentation tasks." @default.
- W4300592870 created "2022-10-03" @default.
- W4300592870 creator A5011819787 @default.
- W4300592870 creator A5030040261 @default.
- W4300592870 creator A5056969005 @default.
- W4300592870 date "2021-10-22" @default.
- W4300592870 modified "2023-10-12" @default.
- W4300592870 title "Semi-Supervised Semantic Segmentation of Vessel Images using Leaking Perturbations" @default.
- W4300592870 doi "https://doi.org/10.48550/arxiv.2110.11998" @default.
- W4300592870 hasPublicationYear "2021" @default.
- W4300592870 type Work @default.
- W4300592870 citedByCount "0" @default.
- W4300592870 crossrefType "posted-content" @default.
- W4300592870 hasAuthorship W4300592870A5011819787 @default.
- W4300592870 hasAuthorship W4300592870A5030040261 @default.
- W4300592870 hasAuthorship W4300592870A5056969005 @default.
- W4300592870 hasBestOaLocation W43005928701 @default.
- W4300592870 hasConcept C108583219 @default.
- W4300592870 hasConcept C119857082 @default.
- W4300592870 hasConcept C121332964 @default.
- W4300592870 hasConcept C13280743 @default.
- W4300592870 hasConcept C153180895 @default.
- W4300592870 hasConcept C154945302 @default.
- W4300592870 hasConcept C162324750 @default.
- W4300592870 hasConcept C163258240 @default.
- W4300592870 hasConcept C185798385 @default.
- W4300592870 hasConcept C187736073 @default.
- W4300592870 hasConcept C205649164 @default.
- W4300592870 hasConcept C26517878 @default.
- W4300592870 hasConcept C2776135515 @default.
- W4300592870 hasConcept C2776436953 @default.
- W4300592870 hasConcept C2779803651 @default.
- W4300592870 hasConcept C2780451532 @default.
- W4300592870 hasConcept C2780992000 @default.
- W4300592870 hasConcept C38652104 @default.
- W4300592870 hasConcept C41008148 @default.
- W4300592870 hasConcept C62520636 @default.
- W4300592870 hasConcept C76155785 @default.
- W4300592870 hasConcept C89600930 @default.
- W4300592870 hasConcept C94915269 @default.
- W4300592870 hasConceptScore W4300592870C108583219 @default.
- W4300592870 hasConceptScore W4300592870C119857082 @default.
- W4300592870 hasConceptScore W4300592870C121332964 @default.
- W4300592870 hasConceptScore W4300592870C13280743 @default.
- W4300592870 hasConceptScore W4300592870C153180895 @default.
- W4300592870 hasConceptScore W4300592870C154945302 @default.
- W4300592870 hasConceptScore W4300592870C162324750 @default.
- W4300592870 hasConceptScore W4300592870C163258240 @default.
- W4300592870 hasConceptScore W4300592870C185798385 @default.
- W4300592870 hasConceptScore W4300592870C187736073 @default.
- W4300592870 hasConceptScore W4300592870C205649164 @default.
- W4300592870 hasConceptScore W4300592870C26517878 @default.
- W4300592870 hasConceptScore W4300592870C2776135515 @default.
- W4300592870 hasConceptScore W4300592870C2776436953 @default.
- W4300592870 hasConceptScore W4300592870C2779803651 @default.
- W4300592870 hasConceptScore W4300592870C2780451532 @default.
- W4300592870 hasConceptScore W4300592870C2780992000 @default.
- W4300592870 hasConceptScore W4300592870C38652104 @default.
- W4300592870 hasConceptScore W4300592870C41008148 @default.
- W4300592870 hasConceptScore W4300592870C62520636 @default.
- W4300592870 hasConceptScore W4300592870C76155785 @default.
- W4300592870 hasConceptScore W4300592870C89600930 @default.
- W4300592870 hasConceptScore W4300592870C94915269 @default.
- W4300592870 hasLocation W43005928701 @default.
- W4300592870 hasOpenAccess W4300592870 @default.
- W4300592870 hasPrimaryLocation W43005928701 @default.
- W4300592870 hasRelatedWork W2619371851 @default.
- W4300592870 hasRelatedWork W2790662084 @default.
- W4300592870 hasRelatedWork W2948658236 @default.
- W4300592870 hasRelatedWork W3005685053 @default.
- W4300592870 hasRelatedWork W3175491752 @default.
- W4300592870 hasRelatedWork W4223943233 @default.
- W4300592870 hasRelatedWork W4293211451 @default.
- W4300592870 hasRelatedWork W4312200629 @default.
- W4300592870 hasRelatedWork W4319600986 @default.
- W4300592870 hasRelatedWork W4360585206 @default.
- W4300592870 isParatext "false" @default.
- W4300592870 isRetracted "false" @default.
- W4300592870 workType "article" @default.