Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320853889> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4320853889 abstract "Self-supervised learning, which is strikingly referred to as the dark matter of intelligence, is gaining more attention in biomedical applications of deep learning. In this work, we introduce a novel self-supervision objective for the analysis of cells in biomedical microscopy images. We propose training deep learning models to pseudo-colorize masked cells. We use a physics-informed pseudo-spectral colormap that is well suited for colorizing cell topology. Our experiments reveal that approximating semantic segmentation by pseudo-colorization is beneficial for subsequent fine-tuning on cell detection. Inspired by the recent success of masked image modeling, we additionally mask out cell parts and train to reconstruct these parts to further enrich the learned representations. We compare our pre-training method with self-supervised frameworks including contrastive learning (SimCLR), masked autoencoders (MAEs), and edge-based self-supervision. We build upon our previous work and train hybrid models for cell detection, which contain both convolutional and vision transformer modules. Our pre-training method can outperform SimCLR, MAE-like masked image modeling, and edge-based self-supervision when pre-training on a diverse set of six fluorescence microscopy datasets. Code is available at: https://github.com/roydenwa/pseudo-colorize-masked-cells" @default.
- W4320853889 created "2023-02-16" @default.
- W4320853889 creator A5074130831 @default.
- W4320853889 creator A5085573091 @default.
- W4320853889 creator A5091574711 @default.
- W4320853889 date "2023-02-12" @default.
- W4320853889 modified "2023-09-30" @default.
- W4320853889 title "Self-supervised pseudo-colorizing of masked cells" @default.
- W4320853889 doi "https://doi.org/10.1371/journal.pone.0290561" @default.
- W4320853889 hasPublicationYear "2023" @default.
- W4320853889 type Work @default.
- W4320853889 citedByCount "0" @default.
- W4320853889 crossrefType "posted-content" @default.
- W4320853889 hasAuthorship W4320853889A5074130831 @default.
- W4320853889 hasAuthorship W4320853889A5085573091 @default.
- W4320853889 hasAuthorship W4320853889A5091574711 @default.
- W4320853889 hasBestOaLocation W43208538891 @default.
- W4320853889 hasConcept C108583219 @default.
- W4320853889 hasConcept C119857082 @default.
- W4320853889 hasConcept C121332964 @default.
- W4320853889 hasConcept C136389625 @default.
- W4320853889 hasConcept C153180895 @default.
- W4320853889 hasConcept C154945302 @default.
- W4320853889 hasConcept C162307627 @default.
- W4320853889 hasConcept C165801399 @default.
- W4320853889 hasConcept C177264268 @default.
- W4320853889 hasConcept C199360897 @default.
- W4320853889 hasConcept C2776760102 @default.
- W4320853889 hasConcept C41008148 @default.
- W4320853889 hasConcept C50644808 @default.
- W4320853889 hasConcept C62520636 @default.
- W4320853889 hasConcept C66322947 @default.
- W4320853889 hasConcept C81363708 @default.
- W4320853889 hasConcept C89600930 @default.
- W4320853889 hasConceptScore W4320853889C108583219 @default.
- W4320853889 hasConceptScore W4320853889C119857082 @default.
- W4320853889 hasConceptScore W4320853889C121332964 @default.
- W4320853889 hasConceptScore W4320853889C136389625 @default.
- W4320853889 hasConceptScore W4320853889C153180895 @default.
- W4320853889 hasConceptScore W4320853889C154945302 @default.
- W4320853889 hasConceptScore W4320853889C162307627 @default.
- W4320853889 hasConceptScore W4320853889C165801399 @default.
- W4320853889 hasConceptScore W4320853889C177264268 @default.
- W4320853889 hasConceptScore W4320853889C199360897 @default.
- W4320853889 hasConceptScore W4320853889C2776760102 @default.
- W4320853889 hasConceptScore W4320853889C41008148 @default.
- W4320853889 hasConceptScore W4320853889C50644808 @default.
- W4320853889 hasConceptScore W4320853889C62520636 @default.
- W4320853889 hasConceptScore W4320853889C66322947 @default.
- W4320853889 hasConceptScore W4320853889C81363708 @default.
- W4320853889 hasConceptScore W4320853889C89600930 @default.
- W4320853889 hasLocation W43208538891 @default.
- W4320853889 hasLocation W43208538892 @default.
- W4320853889 hasLocation W43208538893 @default.
- W4320853889 hasOpenAccess W4320853889 @default.
- W4320853889 hasPrimaryLocation W43208538891 @default.
- W4320853889 hasRelatedWork W2731899572 @default.
- W4320853889 hasRelatedWork W2999805992 @default.
- W4320853889 hasRelatedWork W3116150086 @default.
- W4320853889 hasRelatedWork W3133861977 @default.
- W4320853889 hasRelatedWork W3192794374 @default.
- W4320853889 hasRelatedWork W4200173597 @default.
- W4320853889 hasRelatedWork W4220686584 @default.
- W4320853889 hasRelatedWork W4246751904 @default.
- W4320853889 hasRelatedWork W4312417841 @default.
- W4320853889 hasRelatedWork W4321369474 @default.
- W4320853889 isParatext "false" @default.
- W4320853889 isRetracted "false" @default.
- W4320853889 workType "article" @default.