Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076082> ?p ?o ?g. }
- W4386076082 abstract "Multi-class cell detection and counting is an essential task for many pathological diagnoses. Manual counting is tedious and often leads to inter-observer variations among pathologists. While there exist multiple, general-purpose, deep learning-based object detection and counting methods, they may not readily transfer to detecting and counting cells in medical images, due to the limited data, presence of tiny overlapping objects, multiple cell types, severe class-imbalance, minute differences in size/shape of cells, etc. In response, we propose guided posterior regularization (DEGPR), which assists an object detector by guiding it to exploit discriminative features among cells. The features may be pathologist-provided or inferred directly from visual data. We validate our model on two publicly available datasets (CoNSeP and MoNuSAC), and on MuCeD, a novel dataset that we contribute. MuCeD consists of 55 biopsy images of the human duodenum for predicting celiac disease. We perform extensive experimentation with three object detection baselines on three datasets to show that DeGPR is model-agnostic, and consistently improves baselines obtaining up to 9% (absolute) mAP gains." @default.
- W4386076082 created "2023-08-23" @default.
- W4386076082 creator A5002751454 @default.
- W4386076082 creator A5009844970 @default.
- W4386076082 creator A5015279222 @default.
- W4386076082 creator A5042262991 @default.
- W4386076082 creator A5059852221 @default.
- W4386076082 creator A5066928459 @default.
- W4386076082 creator A5087793768 @default.
- W4386076082 date "2023-06-01" @default.
- W4386076082 modified "2023-10-01" @default.
- W4386076082 title "DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting" @default.
- W4386076082 cites W1965007454 @default.
- W4386076082 cites W1993351885 @default.
- W4386076082 cites W2102605133 @default.
- W4386076082 cites W2194775991 @default.
- W4386076082 cites W2248620004 @default.
- W4386076082 cites W2312404985 @default.
- W4386076082 cites W2346062110 @default.
- W4386076082 cites W2347064614 @default.
- W4386076082 cites W2398921440 @default.
- W4386076082 cites W2592929672 @default.
- W4386076082 cites W2756468276 @default.
- W4386076082 cites W2789089586 @default.
- W4386076082 cites W2913510405 @default.
- W4386076082 cites W2939411050 @default.
- W4386076082 cites W2939549759 @default.
- W4386076082 cites W2962716568 @default.
- W4386076082 cites W2963037989 @default.
- W4386076082 cites W2963351448 @default.
- W4386076082 cites W2964189045 @default.
- W4386076082 cites W2964324957 @default.
- W4386076082 cites W2974825848 @default.
- W4386076082 cites W3005287255 @default.
- W4386076082 cites W3034971973 @default.
- W4386076082 cites W3043056841 @default.
- W4386076082 cites W3090681715 @default.
- W4386076082 cites W3100084586 @default.
- W4386076082 cites W3131663009 @default.
- W4386076082 cites W3170293501 @default.
- W4386076082 cites W3175593095 @default.
- W4386076082 cites W3212240274 @default.
- W4386076082 cites W3216149514 @default.
- W4386076082 cites W3216649800 @default.
- W4386076082 cites W4241721398 @default.
- W4386076082 cites W4292829085 @default.
- W4386076082 doi "https://doi.org/10.1109/cvpr52729.2023.02290" @default.
- W4386076082 hasPublicationYear "2023" @default.
- W4386076082 type Work @default.
- W4386076082 citedByCount "1" @default.
- W4386076082 countsByYear W43860760822023 @default.
- W4386076082 crossrefType "proceedings-article" @default.
- W4386076082 hasAuthorship W4386076082A5002751454 @default.
- W4386076082 hasAuthorship W4386076082A5009844970 @default.
- W4386076082 hasAuthorship W4386076082A5015279222 @default.
- W4386076082 hasAuthorship W4386076082A5042262991 @default.
- W4386076082 hasAuthorship W4386076082A5059852221 @default.
- W4386076082 hasAuthorship W4386076082A5066928459 @default.
- W4386076082 hasAuthorship W4386076082A5087793768 @default.
- W4386076082 hasConcept C142724271 @default.
- W4386076082 hasConcept C150899416 @default.
- W4386076082 hasConcept C153180895 @default.
- W4386076082 hasConcept C154945302 @default.
- W4386076082 hasConcept C165696696 @default.
- W4386076082 hasConcept C2776135515 @default.
- W4386076082 hasConcept C2776151529 @default.
- W4386076082 hasConcept C31601959 @default.
- W4386076082 hasConcept C31972630 @default.
- W4386076082 hasConcept C38652104 @default.
- W4386076082 hasConcept C41008148 @default.
- W4386076082 hasConcept C534262118 @default.
- W4386076082 hasConcept C71924100 @default.
- W4386076082 hasConcept C97931131 @default.
- W4386076082 hasConceptScore W4386076082C142724271 @default.
- W4386076082 hasConceptScore W4386076082C150899416 @default.
- W4386076082 hasConceptScore W4386076082C153180895 @default.
- W4386076082 hasConceptScore W4386076082C154945302 @default.
- W4386076082 hasConceptScore W4386076082C165696696 @default.
- W4386076082 hasConceptScore W4386076082C2776135515 @default.
- W4386076082 hasConceptScore W4386076082C2776151529 @default.
- W4386076082 hasConceptScore W4386076082C31601959 @default.
- W4386076082 hasConceptScore W4386076082C31972630 @default.
- W4386076082 hasConceptScore W4386076082C38652104 @default.
- W4386076082 hasConceptScore W4386076082C41008148 @default.
- W4386076082 hasConceptScore W4386076082C534262118 @default.
- W4386076082 hasConceptScore W4386076082C71924100 @default.
- W4386076082 hasConceptScore W4386076082C97931131 @default.
- W4386076082 hasFunder F4320320720 @default.
- W4386076082 hasLocation W43860760821 @default.
- W4386076082 hasOpenAccess W4386076082 @default.
- W4386076082 hasPrimaryLocation W43860760821 @default.
- W4386076082 hasRelatedWork W1972656095 @default.
- W4386076082 hasRelatedWork W2024160000 @default.
- W4386076082 hasRelatedWork W2061273563 @default.
- W4386076082 hasRelatedWork W2285052147 @default.
- W4386076082 hasRelatedWork W2729514902 @default.
- W4386076082 hasRelatedWork W2743258233 @default.
- W4386076082 hasRelatedWork W2773500201 @default.
- W4386076082 hasRelatedWork W2998168123 @default.
- W4386076082 hasRelatedWork W4287995534 @default.