Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217120382> ?p ?o ?g. }
- W3217120382 endingPage "652" @default.
- W3217120382 startingPage "642" @default.
- W3217120382 abstract "Abstract Species classification is an important task which is the foundation of industrial, commercial, ecological and scientific applications involving the study of species distributions, dynamics and evolution. While conventional approaches for this task use off‐the‐shelf machine learning (ML) methods such as existing Convolutional Neural Network (ConvNet) architectures, there is an opportunity to inform the ConvNet architecture using our knowledge of biological hierarchies among taxonomic classes. In this work, we propose a new approach for species classification termed hierarchy‐guided neural network ( HGNN ), which infuses hierarchical taxonomic information into the neural network's training to guide the structure and relationships among the extracted features. We perform extensive experiments on an illustrative use‐case of classifying fish species to demonstrate that HGNN outperforms conventional ConvNet models in terms of classification accuracy, especially under scarce training data conditions. We also observe that HGNN shows better resilience to adversarial occlusions, when some of the most informative patch regions of the image are intentionally blocked and their effect on classification accuracy is studied." @default.
- W3217120382 created "2021-12-06" @default.
- W3217120382 creator A5003178859 @default.
- W3217120382 creator A5014812866 @default.
- W3217120382 creator A5015961414 @default.
- W3217120382 creator A5020099887 @default.
- W3217120382 creator A5035913440 @default.
- W3217120382 creator A5037935786 @default.
- W3217120382 creator A5049470689 @default.
- W3217120382 creator A5057416419 @default.
- W3217120382 creator A5064934412 @default.
- W3217120382 creator A5067789366 @default.
- W3217120382 creator A5081622450 @default.
- W3217120382 date "2021-12-05" @default.
- W3217120382 modified "2023-09-27" @default.
- W3217120382 title "Hierarchy‐guided neural network for species classification" @default.
- W3217120382 cites W1535874833 @default.
- W3217120382 cites W1595975550 @default.
- W3217120382 cites W2056144381 @default.
- W3217120382 cites W2074072306 @default.
- W3217120382 cites W2081778808 @default.
- W3217120382 cites W2097117768 @default.
- W3217120382 cites W2102605133 @default.
- W3217120382 cites W2108598243 @default.
- W3217120382 cites W2114315281 @default.
- W3217120382 cites W2117580587 @default.
- W3217120382 cites W2127692403 @default.
- W3217120382 cites W2133059825 @default.
- W3217120382 cites W2150766729 @default.
- W3217120382 cites W2171144131 @default.
- W3217120382 cites W2194775991 @default.
- W3217120382 cites W2528543588 @default.
- W3217120382 cites W2549139847 @default.
- W3217120382 cites W2594982232 @default.
- W3217120382 cites W2728026583 @default.
- W3217120382 cites W2734256217 @default.
- W3217120382 cites W2765521864 @default.
- W3217120382 cites W2777483969 @default.
- W3217120382 cites W2803572653 @default.
- W3217120382 cites W2887280559 @default.
- W3217120382 cites W2890356255 @default.
- W3217120382 cites W2897654901 @default.
- W3217120382 cites W2903959061 @default.
- W3217120382 cites W2920741983 @default.
- W3217120382 cites W2954959100 @default.
- W3217120382 cites W2962858109 @default.
- W3217120382 cites W2963037989 @default.
- W3217120382 cites W2963446712 @default.
- W3217120382 cites W2986670051 @default.
- W3217120382 cites W3014286955 @default.
- W3217120382 cites W3026596360 @default.
- W3217120382 cites W3033387047 @default.
- W3217120382 cites W3034942609 @default.
- W3217120382 cites W3160672850 @default.
- W3217120382 cites W3214469933 @default.
- W3217120382 cites W78661028 @default.
- W3217120382 doi "https://doi.org/10.1111/2041-210x.13768" @default.
- W3217120382 hasPublicationYear "2021" @default.
- W3217120382 type Work @default.
- W3217120382 sameAs 3217120382 @default.
- W3217120382 citedByCount "2" @default.
- W3217120382 countsByYear W32171203822022 @default.
- W3217120382 countsByYear W32171203822023 @default.
- W3217120382 crossrefType "journal-article" @default.
- W3217120382 hasAuthorship W3217120382A5003178859 @default.
- W3217120382 hasAuthorship W3217120382A5014812866 @default.
- W3217120382 hasAuthorship W3217120382A5015961414 @default.
- W3217120382 hasAuthorship W3217120382A5020099887 @default.
- W3217120382 hasAuthorship W3217120382A5035913440 @default.
- W3217120382 hasAuthorship W3217120382A5037935786 @default.
- W3217120382 hasAuthorship W3217120382A5049470689 @default.
- W3217120382 hasAuthorship W3217120382A5057416419 @default.
- W3217120382 hasAuthorship W3217120382A5064934412 @default.
- W3217120382 hasAuthorship W3217120382A5067789366 @default.
- W3217120382 hasAuthorship W3217120382A5081622450 @default.
- W3217120382 hasBestOaLocation W32171203821 @default.
- W3217120382 hasConcept C115961682 @default.
- W3217120382 hasConcept C119857082 @default.
- W3217120382 hasConcept C154945302 @default.
- W3217120382 hasConcept C162324750 @default.
- W3217120382 hasConcept C187736073 @default.
- W3217120382 hasConcept C18903297 @default.
- W3217120382 hasConcept C189592816 @default.
- W3217120382 hasConcept C2780451532 @default.
- W3217120382 hasConcept C31170391 @default.
- W3217120382 hasConcept C34447519 @default.
- W3217120382 hasConcept C41008148 @default.
- W3217120382 hasConcept C48702757 @default.
- W3217120382 hasConcept C50644808 @default.
- W3217120382 hasConcept C71640776 @default.
- W3217120382 hasConcept C75294576 @default.
- W3217120382 hasConcept C78458016 @default.
- W3217120382 hasConcept C81363708 @default.
- W3217120382 hasConcept C86803240 @default.
- W3217120382 hasConceptScore W3217120382C115961682 @default.
- W3217120382 hasConceptScore W3217120382C119857082 @default.
- W3217120382 hasConceptScore W3217120382C154945302 @default.
- W3217120382 hasConceptScore W3217120382C162324750 @default.