Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287724534> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4287724534 abstract "Deep learning techniques have been successfully deployed for automating plant stress identification and quantification. In recent years, there is a growing push towards training models that are interpretable -i.e. that justify their classification decisions by visually highlighting image features that were crucial for classification decisions. The expectation is that trained network models utilize image features that mimic visual cues used by plant pathologists. In this work, we compare some of the most popular interpretability methods: Saliency Maps, SmoothGrad, Guided Backpropogation, Deep Taylor Decomposition, Integrated Gradients, Layer-wise Relevance Propagation and Gradient times Input, for interpreting the deep learning model. We train a DenseNet-121 network for the classification of eight different soybean stresses (biotic and abiotic). Using a dataset consisting of 16,573 RGB images of healthy and stressed soybean leaflets captured under controlled conditions, we obtained an overall classification accuracy of 95.05 %. For a diverse subset of the test data, we compared the important features with those identified by a human expert. We observed that most interpretability methods identify the infected regions of the leaf as important features for some -- but not all -- of the correctly classified images. For some images, the output of the interpretability methods indicated that spurious feature correlations may have been used to correctly classify them. Although the output explanation maps of these interpretability methods may be different from each other for a given image, we advocate the use of these interpretability methods as `hypothesis generation' mechanisms that can drive scientific insight." @default.
- W4287724534 created "2022-07-26" @default.
- W4287724534 creator A5022988426 @default.
- W4287724534 creator A5027870420 @default.
- W4287724534 creator A5052127003 @default.
- W4287724534 creator A5081037761 @default.
- W4287724534 creator A5091680686 @default.
- W4287724534 date "2020-07-11" @default.
- W4287724534 modified "2023-10-17" @default.
- W4287724534 title "Usefulness of interpretability methods to explain deep learning based plant stress phenotyping" @default.
- W4287724534 doi "https://doi.org/10.48550/arxiv.2007.05729" @default.
- W4287724534 hasPublicationYear "2020" @default.
- W4287724534 type Work @default.
- W4287724534 citedByCount "1" @default.
- W4287724534 countsByYear W42877245342023 @default.
- W4287724534 crossrefType "posted-content" @default.
- W4287724534 hasAuthorship W4287724534A5022988426 @default.
- W4287724534 hasAuthorship W4287724534A5027870420 @default.
- W4287724534 hasAuthorship W4287724534A5052127003 @default.
- W4287724534 hasAuthorship W4287724534A5081037761 @default.
- W4287724534 hasAuthorship W4287724534A5091680686 @default.
- W4287724534 hasBestOaLocation W42877245341 @default.
- W4287724534 hasConcept C108583219 @default.
- W4287724534 hasConcept C115961682 @default.
- W4287724534 hasConcept C116834253 @default.
- W4287724534 hasConcept C119857082 @default.
- W4287724534 hasConcept C138885662 @default.
- W4287724534 hasConcept C153180895 @default.
- W4287724534 hasConcept C154945302 @default.
- W4287724534 hasConcept C2776401178 @default.
- W4287724534 hasConcept C2781067378 @default.
- W4287724534 hasConcept C41008148 @default.
- W4287724534 hasConcept C41895202 @default.
- W4287724534 hasConcept C59822182 @default.
- W4287724534 hasConcept C75294576 @default.
- W4287724534 hasConcept C86803240 @default.
- W4287724534 hasConcept C97256817 @default.
- W4287724534 hasConceptScore W4287724534C108583219 @default.
- W4287724534 hasConceptScore W4287724534C115961682 @default.
- W4287724534 hasConceptScore W4287724534C116834253 @default.
- W4287724534 hasConceptScore W4287724534C119857082 @default.
- W4287724534 hasConceptScore W4287724534C138885662 @default.
- W4287724534 hasConceptScore W4287724534C153180895 @default.
- W4287724534 hasConceptScore W4287724534C154945302 @default.
- W4287724534 hasConceptScore W4287724534C2776401178 @default.
- W4287724534 hasConceptScore W4287724534C2781067378 @default.
- W4287724534 hasConceptScore W4287724534C41008148 @default.
- W4287724534 hasConceptScore W4287724534C41895202 @default.
- W4287724534 hasConceptScore W4287724534C59822182 @default.
- W4287724534 hasConceptScore W4287724534C75294576 @default.
- W4287724534 hasConceptScore W4287724534C86803240 @default.
- W4287724534 hasConceptScore W4287724534C97256817 @default.
- W4287724534 hasLocation W42877245341 @default.
- W4287724534 hasLocation W42877245342 @default.
- W4287724534 hasOpenAccess W4287724534 @default.
- W4287724534 hasPrimaryLocation W42877245341 @default.
- W4287724534 hasRelatedWork W2605281151 @default.
- W4287724534 hasRelatedWork W2911583982 @default.
- W4287724534 hasRelatedWork W2997541400 @default.
- W4287724534 hasRelatedWork W3006943036 @default.
- W4287724534 hasRelatedWork W3126602623 @default.
- W4287724534 hasRelatedWork W3191046242 @default.
- W4287724534 hasRelatedWork W3208423683 @default.
- W4287724534 hasRelatedWork W4213225422 @default.
- W4287724534 hasRelatedWork W4294031299 @default.
- W4287724534 hasRelatedWork W4299487748 @default.
- W4287724534 isParatext "false" @default.
- W4287724534 isRetracted "false" @default.
- W4287724534 workType "article" @default.