Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360981379> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4360981379 endingPage "312" @default.
- W4360981379 startingPage "305" @default.
- W4360981379 abstract "<p>It is a new problem for deep learning to train a model on a small number of known targets to detect this object. Many recent studies are based on fine-tuning methods to solve. However, there is a lot of redundant information in the model during feature extraction, which will aggravate the difficulty of fine-tuning the model. Moreover, the neural network using the cross-entropy loss function classifier trained in few shots is prone to overfitting. We use the RS structure to reduce the number of channels in the model to reduce the repeated features in feature extraction. In addition, we use the Pearson distance function to calculate the classification loss of the model, to use the nonparametric method to reduce the number of parameters and prevent overfitting. Experimental results show that our method is better than the previous methods on Pascal VOC and FSOD datasets.</p> <p> </p>" @default.
- W4360981379 created "2023-03-30" @default.
- W4360981379 creator A5016381443 @default.
- W4360981379 creator A5030103799 @default.
- W4360981379 creator A5033195473 @default.
- W4360981379 creator A5037029065 @default.
- W4360981379 creator A5075564977 @default.
- W4360981379 date "2023-03-01" @default.
- W4360981379 modified "2023-10-17" @default.
- W4360981379 title "Few Shot Object Detection via a Generalized Feature Extraction Net" @default.
- W4360981379 doi "https://doi.org/10.53106/160792642023032402009" @default.
- W4360981379 hasPublicationYear "2023" @default.
- W4360981379 type Work @default.
- W4360981379 citedByCount "0" @default.
- W4360981379 crossrefType "journal-article" @default.
- W4360981379 hasAuthorship W4360981379A5016381443 @default.
- W4360981379 hasAuthorship W4360981379A5030103799 @default.
- W4360981379 hasAuthorship W4360981379A5033195473 @default.
- W4360981379 hasAuthorship W4360981379A5037029065 @default.
- W4360981379 hasAuthorship W4360981379A5075564977 @default.
- W4360981379 hasBestOaLocation W43609813791 @default.
- W4360981379 hasConcept C106301342 @default.
- W4360981379 hasConcept C108583219 @default.
- W4360981379 hasConcept C119857082 @default.
- W4360981379 hasConcept C120665830 @default.
- W4360981379 hasConcept C121332964 @default.
- W4360981379 hasConcept C153180895 @default.
- W4360981379 hasConcept C154945302 @default.
- W4360981379 hasConcept C167981619 @default.
- W4360981379 hasConcept C199360897 @default.
- W4360981379 hasConcept C22019652 @default.
- W4360981379 hasConcept C3019835501 @default.
- W4360981379 hasConcept C41008148 @default.
- W4360981379 hasConcept C50644808 @default.
- W4360981379 hasConcept C52622490 @default.
- W4360981379 hasConcept C62520636 @default.
- W4360981379 hasConcept C75608658 @default.
- W4360981379 hasConcept C81363708 @default.
- W4360981379 hasConcept C95623464 @default.
- W4360981379 hasConceptScore W4360981379C106301342 @default.
- W4360981379 hasConceptScore W4360981379C108583219 @default.
- W4360981379 hasConceptScore W4360981379C119857082 @default.
- W4360981379 hasConceptScore W4360981379C120665830 @default.
- W4360981379 hasConceptScore W4360981379C121332964 @default.
- W4360981379 hasConceptScore W4360981379C153180895 @default.
- W4360981379 hasConceptScore W4360981379C154945302 @default.
- W4360981379 hasConceptScore W4360981379C167981619 @default.
- W4360981379 hasConceptScore W4360981379C199360897 @default.
- W4360981379 hasConceptScore W4360981379C22019652 @default.
- W4360981379 hasConceptScore W4360981379C3019835501 @default.
- W4360981379 hasConceptScore W4360981379C41008148 @default.
- W4360981379 hasConceptScore W4360981379C50644808 @default.
- W4360981379 hasConceptScore W4360981379C52622490 @default.
- W4360981379 hasConceptScore W4360981379C62520636 @default.
- W4360981379 hasConceptScore W4360981379C75608658 @default.
- W4360981379 hasConceptScore W4360981379C81363708 @default.
- W4360981379 hasConceptScore W4360981379C95623464 @default.
- W4360981379 hasIssue "2" @default.
- W4360981379 hasLocation W43609813791 @default.
- W4360981379 hasOpenAccess W4360981379 @default.
- W4360981379 hasPrimaryLocation W43609813791 @default.
- W4360981379 hasRelatedWork W2279398222 @default.
- W4360981379 hasRelatedWork W2742991909 @default.
- W4360981379 hasRelatedWork W2767651786 @default.
- W4360981379 hasRelatedWork W3099765033 @default.
- W4360981379 hasRelatedWork W3156786002 @default.
- W4360981379 hasRelatedWork W4220996320 @default.
- W4360981379 hasRelatedWork W4283701629 @default.
- W4360981379 hasRelatedWork W4299822940 @default.
- W4360981379 hasRelatedWork W4362499066 @default.
- W4360981379 hasRelatedWork W4366492315 @default.
- W4360981379 hasVolume "24" @default.
- W4360981379 isParatext "false" @default.
- W4360981379 isRetracted "false" @default.
- W4360981379 workType "article" @default.