Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386280212> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4386280212 endingPage "107412" @default.
- W4386280212 startingPage "107412" @default.
- W4386280212 abstract "Endoscopy is a widely used technique for the early detection of diseases or robotic-assisted minimally invasive surgery (RMIS). Numerous deep learning (DL)-based research works have been developed for automated diagnosis or processing of endoscopic view. However, existing DL models may suffer from catastrophic forgetting. When new target classes are introduced over time or cross institutions, the performance of old classes may suffer severe degradation. More seriously, data privacy and storage issues may lead to the unavailability of old data when updating the model. Therefore, it is necessary to develop a continual learning (CL) methodology to solve the problem of catastrophic forgetting in endoscopic image segmentation. To tackle this, we propose a Endoscopy Continual Semantic Segmentation (EndoCSS) framework that does not involve the storage and privacy issues of exemplar data. The framework includes a mini-batch pseudo-replay (MB-PR) mechanism and a self-adaptive noisy cross-entropy (SAN-CE) loss. The MB-PR strategy circumvents privacy and storage issues by generating pseudo-replay images through a generative model. Meanwhile, the MB-PR strategy can also correct the model deviation to the replay data and current training data, which is aroused by the significant difference in the amount of current and replay images. Therefore, the model can perform effective representation learning on both new and old tasks. SAN-CE loss can help model fitting by adjusting the model’s output logits, and also improve the robustness of training. Extensive continual semantic segmentation (CSS) experiments on public datasets demonstrate that our method can robustly and effectively address the catastrophic forgetting brought by class increment in endoscopy scenes. The results show that our framework holds excellent potential for real-world deployment in a streaming learning manner." @default.
- W4386280212 created "2023-08-31" @default.
- W4386280212 creator A5012678393 @default.
- W4386280212 creator A5016046812 @default.
- W4386280212 creator A5032340829 @default.
- W4386280212 creator A5036156987 @default.
- W4386280212 creator A5046147392 @default.
- W4386280212 date "2023-10-01" @default.
- W4386280212 modified "2023-09-27" @default.
- W4386280212 title "Rethinking exemplars for continual semantic segmentation in endoscopy scenes: Entropy-based mini-batch pseudo-replay" @default.
- W4386280212 cites W2473930607 @default.
- W4386280212 cites W2560647685 @default.
- W4386280212 cites W2884985635 @default.
- W4386280212 cites W2987543910 @default.
- W4386280212 cites W2996514457 @default.
- W4386280212 cites W3031989616 @default.
- W4386280212 cites W3096831136 @default.
- W4386280212 cites W3133432362 @default.
- W4386280212 cites W3162286397 @default.
- W4386280212 cites W3196792983 @default.
- W4386280212 cites W3197664895 @default.
- W4386280212 cites W3208656753 @default.
- W4386280212 cites W4210528082 @default.
- W4386280212 cites W4220880215 @default.
- W4386280212 cites W4294343881 @default.
- W4386280212 doi "https://doi.org/10.1016/j.compbiomed.2023.107412" @default.
- W4386280212 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37696180" @default.
- W4386280212 hasPublicationYear "2023" @default.
- W4386280212 type Work @default.
- W4386280212 citedByCount "0" @default.
- W4386280212 crossrefType "journal-article" @default.
- W4386280212 hasAuthorship W4386280212A5012678393 @default.
- W4386280212 hasAuthorship W4386280212A5016046812 @default.
- W4386280212 hasAuthorship W4386280212A5032340829 @default.
- W4386280212 hasAuthorship W4386280212A5036156987 @default.
- W4386280212 hasAuthorship W4386280212A5046147392 @default.
- W4386280212 hasConcept C104317684 @default.
- W4386280212 hasConcept C119857082 @default.
- W4386280212 hasConcept C127413603 @default.
- W4386280212 hasConcept C138885662 @default.
- W4386280212 hasConcept C153180895 @default.
- W4386280212 hasConcept C154945302 @default.
- W4386280212 hasConcept C167981619 @default.
- W4386280212 hasConcept C185592680 @default.
- W4386280212 hasConcept C200601418 @default.
- W4386280212 hasConcept C2780505938 @default.
- W4386280212 hasConcept C41008148 @default.
- W4386280212 hasConcept C41895202 @default.
- W4386280212 hasConcept C55493867 @default.
- W4386280212 hasConcept C63479239 @default.
- W4386280212 hasConcept C7149132 @default.
- W4386280212 hasConcept C89600930 @default.
- W4386280212 hasConceptScore W4386280212C104317684 @default.
- W4386280212 hasConceptScore W4386280212C119857082 @default.
- W4386280212 hasConceptScore W4386280212C127413603 @default.
- W4386280212 hasConceptScore W4386280212C138885662 @default.
- W4386280212 hasConceptScore W4386280212C153180895 @default.
- W4386280212 hasConceptScore W4386280212C154945302 @default.
- W4386280212 hasConceptScore W4386280212C167981619 @default.
- W4386280212 hasConceptScore W4386280212C185592680 @default.
- W4386280212 hasConceptScore W4386280212C200601418 @default.
- W4386280212 hasConceptScore W4386280212C2780505938 @default.
- W4386280212 hasConceptScore W4386280212C41008148 @default.
- W4386280212 hasConceptScore W4386280212C41895202 @default.
- W4386280212 hasConceptScore W4386280212C55493867 @default.
- W4386280212 hasConceptScore W4386280212C63479239 @default.
- W4386280212 hasConceptScore W4386280212C7149132 @default.
- W4386280212 hasConceptScore W4386280212C89600930 @default.
- W4386280212 hasLocation W43862802121 @default.
- W4386280212 hasLocation W43862802122 @default.
- W4386280212 hasOpenAccess W4386280212 @default.
- W4386280212 hasPrimaryLocation W43862802121 @default.
- W4386280212 hasRelatedWork W1841747458 @default.
- W4386280212 hasRelatedWork W2005485921 @default.
- W4386280212 hasRelatedWork W2466259538 @default.
- W4386280212 hasRelatedWork W2961085424 @default.
- W4386280212 hasRelatedWork W4283311345 @default.
- W4386280212 hasRelatedWork W4306674287 @default.
- W4386280212 hasRelatedWork W4382766482 @default.
- W4386280212 hasRelatedWork W4386211615 @default.
- W4386280212 hasRelatedWork W4386270912 @default.
- W4386280212 hasRelatedWork W4224009465 @default.
- W4386280212 hasVolume "165" @default.
- W4386280212 isParatext "false" @default.
- W4386280212 isRetracted "false" @default.
- W4386280212 workType "article" @default.