Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311413103> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W4311413103 abstract "Weakly-supervised learning (WSL) has been proposed to alleviate the conflict between data annotation cost and model performance through employing sparsely-grained (i.e., point-, box-, scribble-wise) supervision and has shown promising performance, particularly in the image segmentation field. However, it is still a very challenging task due to the limited supervision, especially when only a small number of labeled samples are available. Additionally, almost all existing WSL segmentation methods are designed for star-convex structures which are very different from curvilinear structures such as vessels and nerves. In this paper, we propose a novel sparsely annotated segmentation framework for curvilinear structures, named YoloCurvSeg. A very essential component of YoloCurvSeg is image synthesis. Specifically, a background generator delivers image backgrounds that closely match the real distributions through inpainting dilated skeletons. The extracted backgrounds are then combined with randomly emulated curves generated by a Space Colonization Algorithm-based foreground generator and through a multilayer patch-wise contrastive learning synthesizer. In this way, a synthetic dataset with both images and curve segmentation labels is obtained, at the cost of only one or a few noisy skeleton annotations. Finally, a segmenter is trained with the generated dataset and possibly an unlabeled dataset. The proposed YoloCurvSeg is evaluated on four publicly available datasets (OCTA500, CORN, DRIVE and CHASEDB1) and the results show that YoloCurvSeg outperforms state-of-the-art WSL segmentation methods by large margins. With only one noisy skeleton annotation (respectively 0.14%, 0.03%, 1.40%, and 0.65% of the full annotation), YoloCurvSeg achieves more than 97% of the fully-supervised performance on each dataset. Code and datasets will be released at https://github.com/llmir/YoloCurvSeg." @default.
- W4311413103 created "2022-12-26" @default.
- W4311413103 creator A5001406512 @default.
- W4311413103 creator A5025516568 @default.
- W4311413103 creator A5037672272 @default.
- W4311413103 creator A5050401709 @default.
- W4311413103 creator A5058965019 @default.
- W4311413103 creator A5060393400 @default.
- W4311413103 creator A5064221165 @default.
- W4311413103 date "2022-12-11" @default.
- W4311413103 modified "2023-10-16" @default.
- W4311413103 title "YoloCurvSeg: You Only Label One Noisy Skeleton for Vessel-style Curvilinear Structure Segmentation" @default.
- W4311413103 doi "https://doi.org/10.48550/arxiv.2212.05566" @default.
- W4311413103 hasPublicationYear "2022" @default.
- W4311413103 type Work @default.
- W4311413103 citedByCount "0" @default.
- W4311413103 crossrefType "posted-content" @default.
- W4311413103 hasAuthorship W4311413103A5001406512 @default.
- W4311413103 hasAuthorship W4311413103A5025516568 @default.
- W4311413103 hasAuthorship W4311413103A5037672272 @default.
- W4311413103 hasAuthorship W4311413103A5050401709 @default.
- W4311413103 hasAuthorship W4311413103A5058965019 @default.
- W4311413103 hasAuthorship W4311413103A5060393400 @default.
- W4311413103 hasAuthorship W4311413103A5064221165 @default.
- W4311413103 hasBestOaLocation W43114131031 @default.
- W4311413103 hasConcept C121332964 @default.
- W4311413103 hasConcept C153180895 @default.
- W4311413103 hasConcept C154945302 @default.
- W4311413103 hasConcept C163258240 @default.
- W4311413103 hasConcept C2776321320 @default.
- W4311413103 hasConcept C2780992000 @default.
- W4311413103 hasConcept C41008148 @default.
- W4311413103 hasConcept C62520636 @default.
- W4311413103 hasConcept C89600930 @default.
- W4311413103 hasConceptScore W4311413103C121332964 @default.
- W4311413103 hasConceptScore W4311413103C153180895 @default.
- W4311413103 hasConceptScore W4311413103C154945302 @default.
- W4311413103 hasConceptScore W4311413103C163258240 @default.
- W4311413103 hasConceptScore W4311413103C2776321320 @default.
- W4311413103 hasConceptScore W4311413103C2780992000 @default.
- W4311413103 hasConceptScore W4311413103C41008148 @default.
- W4311413103 hasConceptScore W4311413103C62520636 @default.
- W4311413103 hasConceptScore W4311413103C89600930 @default.
- W4311413103 hasLocation W43114131031 @default.
- W4311413103 hasLocation W43114131032 @default.
- W4311413103 hasOpenAccess W4311413103 @default.
- W4311413103 hasPrimaryLocation W43114131031 @default.
- W4311413103 hasRelatedWork W1529400504 @default.
- W4311413103 hasRelatedWork W1892467659 @default.
- W4311413103 hasRelatedWork W2390459957 @default.
- W4311413103 hasRelatedWork W2394327295 @default.
- W4311413103 hasRelatedWork W2808586768 @default.
- W4311413103 hasRelatedWork W2998403542 @default.
- W4311413103 hasRelatedWork W3159311316 @default.
- W4311413103 hasRelatedWork W4287199417 @default.
- W4311413103 hasRelatedWork W4353114794 @default.
- W4311413103 hasRelatedWork W4386071981 @default.
- W4311413103 isParatext "false" @default.
- W4311413103 isRetracted "false" @default.
- W4311413103 workType "article" @default.