Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210021892> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3210021892 abstract "Automatic classification of pests and plants (both healthy and diseased) is of paramount importance in agriculture to improve yield. Conventional deep learning models based on convolutional neural networks require thousands of labeled examples per category. In this work we propose a method to learn from a few samples to automatically classify different pests, plants, and their diseases, using Few-Shot Learning (FSL). We learn a feature extractor to generate embeddings and then update the embeddings using Transformers. Using Mahalanobis distance, a class-covariance-based metric, we then calculate the similarity of the transformed embeddings with the embedding of the image to be classified. Using our proposed architecture, we conduct extensive experiments on multiple datasets showing the effectiveness of our proposed model. We conduct 42 experiments in total to comprehensively analyze the model and it achieves up to 14% and 24% performance gains on few-shot image classification benchmarks on two datasets.We also compile a new FSL dataset containing images of healthy and diseased plants taken in real-world settings. Using our proposed architecture which has been shown to outperform several existing FSL architectures in agriculture, we provide strong baselines on our newly proposed dataset." @default.
- W3210021892 created "2021-11-08" @default.
- W3210021892 creator A5008151704 @default.
- W3210021892 creator A5059257648 @default.
- W3210021892 date "2021-10-01" @default.
- W3210021892 modified "2023-10-18" @default.
- W3210021892 title "Multi-Domain Few-Shot Learning and Dataset for Agricultural Applications" @default.
- W3210021892 cites W2115733720 @default.
- W3210021892 cites W2117539524 @default.
- W3210021892 cites W2166730504 @default.
- W3210021892 cites W2194775991 @default.
- W3210021892 cites W2731165298 @default.
- W3210021892 cites W2789255992 @default.
- W3210021892 cites W2793556064 @default.
- W3210021892 cites W2798836702 @default.
- W3210021892 cites W2883992358 @default.
- W3210021892 cites W2954934222 @default.
- W3210021892 cites W2962762077 @default.
- W3210021892 cites W2963070905 @default.
- W3210021892 cites W2971516800 @default.
- W3210021892 cites W3001576889 @default.
- W3210021892 cites W3034312118 @default.
- W3210021892 cites W3034587791 @default.
- W3210021892 cites W3035982802 @default.
- W3210021892 cites W3108319047 @default.
- W3210021892 cites W3131151895 @default.
- W3210021892 doi "https://doi.org/10.1109/iccvw54120.2021.00161" @default.
- W3210021892 hasPublicationYear "2021" @default.
- W3210021892 type Work @default.
- W3210021892 sameAs 3210021892 @default.
- W3210021892 citedByCount "12" @default.
- W3210021892 countsByYear W32100218922022 @default.
- W3210021892 countsByYear W32100218922023 @default.
- W3210021892 crossrefType "proceedings-article" @default.
- W3210021892 hasAuthorship W3210021892A5008151704 @default.
- W3210021892 hasAuthorship W3210021892A5059257648 @default.
- W3210021892 hasBestOaLocation W32100218922 @default.
- W3210021892 hasConcept C108583219 @default.
- W3210021892 hasConcept C115961682 @default.
- W3210021892 hasConcept C119857082 @default.
- W3210021892 hasConcept C123657996 @default.
- W3210021892 hasConcept C142362112 @default.
- W3210021892 hasConcept C153180895 @default.
- W3210021892 hasConcept C153349607 @default.
- W3210021892 hasConcept C154945302 @default.
- W3210021892 hasConcept C162324750 @default.
- W3210021892 hasConcept C176217482 @default.
- W3210021892 hasConcept C1921717 @default.
- W3210021892 hasConcept C21547014 @default.
- W3210021892 hasConcept C41008148 @default.
- W3210021892 hasConcept C41608201 @default.
- W3210021892 hasConcept C52622490 @default.
- W3210021892 hasConcept C75294576 @default.
- W3210021892 hasConcept C81363708 @default.
- W3210021892 hasConceptScore W3210021892C108583219 @default.
- W3210021892 hasConceptScore W3210021892C115961682 @default.
- W3210021892 hasConceptScore W3210021892C119857082 @default.
- W3210021892 hasConceptScore W3210021892C123657996 @default.
- W3210021892 hasConceptScore W3210021892C142362112 @default.
- W3210021892 hasConceptScore W3210021892C153180895 @default.
- W3210021892 hasConceptScore W3210021892C153349607 @default.
- W3210021892 hasConceptScore W3210021892C154945302 @default.
- W3210021892 hasConceptScore W3210021892C162324750 @default.
- W3210021892 hasConceptScore W3210021892C176217482 @default.
- W3210021892 hasConceptScore W3210021892C1921717 @default.
- W3210021892 hasConceptScore W3210021892C21547014 @default.
- W3210021892 hasConceptScore W3210021892C41008148 @default.
- W3210021892 hasConceptScore W3210021892C41608201 @default.
- W3210021892 hasConceptScore W3210021892C52622490 @default.
- W3210021892 hasConceptScore W3210021892C75294576 @default.
- W3210021892 hasConceptScore W3210021892C81363708 @default.
- W3210021892 hasLocation W32100218921 @default.
- W3210021892 hasLocation W32100218922 @default.
- W3210021892 hasOpenAccess W3210021892 @default.
- W3210021892 hasPrimaryLocation W32100218921 @default.
- W3210021892 hasRelatedWork W2279398222 @default.
- W3210021892 hasRelatedWork W2412645770 @default.
- W3210021892 hasRelatedWork W2732542196 @default.
- W3210021892 hasRelatedWork W2774265021 @default.
- W3210021892 hasRelatedWork W2800691917 @default.
- W3210021892 hasRelatedWork W2969680539 @default.
- W3210021892 hasRelatedWork W3011074480 @default.
- W3210021892 hasRelatedWork W4299822940 @default.
- W3210021892 hasRelatedWork W4311257506 @default.
- W3210021892 hasRelatedWork W564581980 @default.
- W3210021892 isParatext "false" @default.
- W3210021892 isRetracted "false" @default.
- W3210021892 magId "3210021892" @default.
- W3210021892 workType "article" @default.