Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320483653> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4320483653 abstract "Fully supervised semantic segmentation models require pixel-level annotations that are costly to obtain. As a remedy, weakly supervised semantic segmentation has been proposed, where image-level labels and class activation maps (CAM) can detect discriminative regions for specific class objects. In this paper, we evaluated several CAM methods applied to different convolutional neural networks (CNN) to highlight tissue damage of cod fillets with soft boundaries in MRI. Our results show that different CAM methods produce very different CAM regions, even when applying them to the same CNN model. CAM methods that claim to highlight more of the class object do not necessarily highlight more damaged regions or originate from the same high discriminatory regions, nor do these damaged regions show high agreement across the different CAM methods. Additionally, CAM methods produce damaged regions that do not align with external reference metrics, and even show correlations contrary to what can be expected." @default.
- W4320483653 created "2023-02-14" @default.
- W4320483653 creator A5036055371 @default.
- W4320483653 creator A5044732009 @default.
- W4320483653 creator A5059217328 @default.
- W4320483653 creator A5071360984 @default.
- W4320483653 date "2023-02-13" @default.
- W4320483653 modified "2023-09-25" @default.
- W4320483653 title "Weakly supervised semantic segmentation for MRI: exploring the advantages and disadvantages of class activation maps for biological image segmentation with soft boundaries" @default.
- W4320483653 cites W1745334888 @default.
- W4320483653 cites W1901129140 @default.
- W4320483653 cites W1903029394 @default.
- W4320483653 cites W2037227137 @default.
- W4320483653 cites W2102605133 @default.
- W4320483653 cites W2117539524 @default.
- W4320483653 cites W2168745915 @default.
- W4320483653 cites W2183341477 @default.
- W4320483653 cites W2194775991 @default.
- W4320483653 cites W2295107390 @default.
- W4320483653 cites W2531409750 @default.
- W4320483653 cites W2765793020 @default.
- W4320483653 cites W2794284562 @default.
- W4320483653 cites W2804860796 @default.
- W4320483653 cites W2884367402 @default.
- W4320483653 cites W2902287190 @default.
- W4320483653 cites W2962858109 @default.
- W4320483653 cites W2963037989 @default.
- W4320483653 cites W2963150697 @default.
- W4320483653 cites W2963446712 @default.
- W4320483653 cites W2963727650 @default.
- W4320483653 cites W2964350391 @default.
- W4320483653 cites W2979200397 @default.
- W4320483653 cites W2980189057 @default.
- W4320483653 cites W3034333089 @default.
- W4320483653 cites W3035253074 @default.
- W4320483653 cites W3035665735 @default.
- W4320483653 cites W3095302265 @default.
- W4320483653 cites W3146634043 @default.
- W4320483653 cites W3176482836 @default.
- W4320483653 cites W4320002812 @default.
- W4320483653 cites W639708223 @default.
- W4320483653 doi "https://doi.org/10.1038/s41598-023-29665-y" @default.
- W4320483653 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36781947" @default.
- W4320483653 hasPublicationYear "2023" @default.
- W4320483653 type Work @default.
- W4320483653 citedByCount "1" @default.
- W4320483653 countsByYear W43204836532023 @default.
- W4320483653 crossrefType "journal-article" @default.
- W4320483653 hasAuthorship W4320483653A5036055371 @default.
- W4320483653 hasAuthorship W4320483653A5044732009 @default.
- W4320483653 hasAuthorship W4320483653A5059217328 @default.
- W4320483653 hasAuthorship W4320483653A5071360984 @default.
- W4320483653 hasBestOaLocation W43204836531 @default.
- W4320483653 hasConcept C115961682 @default.
- W4320483653 hasConcept C153180895 @default.
- W4320483653 hasConcept C154945302 @default.
- W4320483653 hasConcept C2777212361 @default.
- W4320483653 hasConcept C2781238097 @default.
- W4320483653 hasConcept C41008148 @default.
- W4320483653 hasConcept C81363708 @default.
- W4320483653 hasConcept C89600930 @default.
- W4320483653 hasConcept C97931131 @default.
- W4320483653 hasConceptScore W4320483653C115961682 @default.
- W4320483653 hasConceptScore W4320483653C153180895 @default.
- W4320483653 hasConceptScore W4320483653C154945302 @default.
- W4320483653 hasConceptScore W4320483653C2777212361 @default.
- W4320483653 hasConceptScore W4320483653C2781238097 @default.
- W4320483653 hasConceptScore W4320483653C41008148 @default.
- W4320483653 hasConceptScore W4320483653C81363708 @default.
- W4320483653 hasConceptScore W4320483653C89600930 @default.
- W4320483653 hasConceptScore W4320483653C97931131 @default.
- W4320483653 hasFunder F4320309820 @default.
- W4320483653 hasIssue "1" @default.
- W4320483653 hasLocation W43204836531 @default.
- W4320483653 hasLocation W43204836532 @default.
- W4320483653 hasLocation W43204836533 @default.
- W4320483653 hasLocation W43204836534 @default.
- W4320483653 hasOpenAccess W4320483653 @default.
- W4320483653 hasPrimaryLocation W43204836531 @default.
- W4320483653 hasRelatedWork W1972656095 @default.
- W4320483653 hasRelatedWork W2024160000 @default.
- W4320483653 hasRelatedWork W2061273563 @default.
- W4320483653 hasRelatedWork W2285052147 @default.
- W4320483653 hasRelatedWork W2729514902 @default.
- W4320483653 hasRelatedWork W2743258233 @default.
- W4320483653 hasRelatedWork W2773500201 @default.
- W4320483653 hasRelatedWork W2998168123 @default.
- W4320483653 hasRelatedWork W4287995534 @default.
- W4320483653 hasRelatedWork W4319301798 @default.
- W4320483653 hasVolume "13" @default.
- W4320483653 isParatext "false" @default.
- W4320483653 isRetracted "false" @default.
- W4320483653 workType "article" @default.