Matches in SemOpenAlex for { <https://semopenalex.org/work/W2772991330> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2772991330 abstract "In this paper, we propose a scale-invariant framework based on Convolutional Neural Networks (CNNs). The network exhibits robustness to scale and resolution variations in data. Previous efforts in achieving scale invariance were made on either integrating several variant-specific CNNs or data augmentation. However, these methods did not solve the fundamental problem that CNNs develop different feature representations for the variants of the same image. The topology proposed by this paper develops a uniform representation for each of the variants of the same image. The uniformity is acquired by concatenating scale-variant and scale-invariant features to enlarge the feature space so that the case when input images are of diverse variations but from the same class can be distinguished from another case when images are of different classes. Higher-order decision boundaries lead to the success of the framework. Experimental results on a challenging dataset substantiates that our framework performs better than traditional frameworks with the same number of free parameters. Our proposed framework can also achieve a higher training efficiency." @default.
- W2772991330 created "2017-12-22" @default.
- W2772991330 creator A5045163085 @default.
- W2772991330 creator A5050364086 @default.
- W2772991330 date "2017-10-01" @default.
- W2772991330 modified "2023-10-18" @default.
- W2772991330 title "A scale-invariant framework for image classification with deep learning" @default.
- W2772991330 cites W1522737968 @default.
- W2772991330 cites W1572398019 @default.
- W2772991330 cites W1755205674 @default.
- W2772991330 cites W1793977698 @default.
- W2772991330 cites W1965732870 @default.
- W2772991330 cites W1966233465 @default.
- W2772991330 cites W1987202160 @default.
- W2772991330 cites W1987309482 @default.
- W2772991330 cites W2023962567 @default.
- W2772991330 cites W2066916495 @default.
- W2772991330 cites W2097117768 @default.
- W2772991330 cites W2109255472 @default.
- W2772991330 cites W2126126729 @default.
- W2772991330 cites W2161753062 @default.
- W2772991330 cites W2194775991 @default.
- W2772991330 cites W2253709148 @default.
- W2772991330 cites W3125537303 @default.
- W2772991330 doi "https://doi.org/10.1109/smc.2017.8122744" @default.
- W2772991330 hasPublicationYear "2017" @default.
- W2772991330 type Work @default.
- W2772991330 sameAs 2772991330 @default.
- W2772991330 citedByCount "2" @default.
- W2772991330 countsByYear W27729913302020 @default.
- W2772991330 countsByYear W27729913302022 @default.
- W2772991330 crossrefType "proceedings-article" @default.
- W2772991330 hasAuthorship W2772991330A5045163085 @default.
- W2772991330 hasAuthorship W2772991330A5050364086 @default.
- W2772991330 hasConcept C105795698 @default.
- W2772991330 hasConcept C108583219 @default.
- W2772991330 hasConcept C115961682 @default.
- W2772991330 hasConcept C135593079 @default.
- W2772991330 hasConcept C153180895 @default.
- W2772991330 hasConcept C154945302 @default.
- W2772991330 hasConcept C190470478 @default.
- W2772991330 hasConcept C205649164 @default.
- W2772991330 hasConcept C2778755073 @default.
- W2772991330 hasConcept C31972630 @default.
- W2772991330 hasConcept C33923547 @default.
- W2772991330 hasConcept C37914503 @default.
- W2772991330 hasConcept C41008148 @default.
- W2772991330 hasConcept C58640448 @default.
- W2772991330 hasConcept C75294576 @default.
- W2772991330 hasConceptScore W2772991330C105795698 @default.
- W2772991330 hasConceptScore W2772991330C108583219 @default.
- W2772991330 hasConceptScore W2772991330C115961682 @default.
- W2772991330 hasConceptScore W2772991330C135593079 @default.
- W2772991330 hasConceptScore W2772991330C153180895 @default.
- W2772991330 hasConceptScore W2772991330C154945302 @default.
- W2772991330 hasConceptScore W2772991330C190470478 @default.
- W2772991330 hasConceptScore W2772991330C205649164 @default.
- W2772991330 hasConceptScore W2772991330C2778755073 @default.
- W2772991330 hasConceptScore W2772991330C31972630 @default.
- W2772991330 hasConceptScore W2772991330C33923547 @default.
- W2772991330 hasConceptScore W2772991330C37914503 @default.
- W2772991330 hasConceptScore W2772991330C41008148 @default.
- W2772991330 hasConceptScore W2772991330C58640448 @default.
- W2772991330 hasConceptScore W2772991330C75294576 @default.
- W2772991330 hasLocation W27729913301 @default.
- W2772991330 hasOpenAccess W2772991330 @default.
- W2772991330 hasPrimaryLocation W27729913301 @default.
- W2772991330 hasRelatedWork W2005185696 @default.
- W2772991330 hasRelatedWork W2049585214 @default.
- W2772991330 hasRelatedWork W2166648532 @default.
- W2772991330 hasRelatedWork W2544283655 @default.
- W2772991330 hasRelatedWork W2732542196 @default.
- W2772991330 hasRelatedWork W2773120646 @default.
- W2772991330 hasRelatedWork W2774265021 @default.
- W2772991330 hasRelatedWork W3111677651 @default.
- W2772991330 hasRelatedWork W3156786002 @default.
- W2772991330 hasRelatedWork W564581980 @default.
- W2772991330 isParatext "false" @default.
- W2772991330 isRetracted "false" @default.
- W2772991330 magId "2772991330" @default.
- W2772991330 workType "article" @default.