Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963559171> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2963559171 endingPage "16" @default.
- W2963559171 startingPage "1" @default.
- W2963559171 abstract "Convolutional neural networks (CNNs) have yielded the excellent performance in a variety of computer vision tasks, where CNNs typically adopt a similar structure consisting of convolution layers, pooling layers and fully connected layers. In this paper, we propose to apply a novel method, namely Hybrid Orthogonal Projection and Estimation (HOPE), to CNNs in order to introduce orthogonality into the CNN structure. The HOPE model can be viewed as a hybrid model to combine feature extraction using orthogonal linear projection with mixture models. It is an effective model to extract useful information from the original high-dimension feature vectors and meanwhile filter out irrelevant noises. In this work, we present three different ways to apply the HOPE models to CNNs, i.e., {em HOPE-Input}, {em single-HOPE-Block} and {em multi-HOPE-Blocks}. For {em HOPE-Input} CNNs, a HOPE layer is directly used right after the input to de-correlate high-dimension input feature vectors. Alternatively, in {em single-HOPE-Block} and {em multi-HOPE-Blocks} CNNs, we consider to use HOPE layers to replace one or more blocks in the CNNs, where one block may include several convolutional layers and one pooling layer. The experimental results on both Cifar-10 and Cifar-100 data sets have shown that the orthogonal constraints imposed by the HOPE layers can significantly improve the performance of CNNs in these image classification tasks (we have achieved one of the best performance when image augmentation has not been applied, and top 5 performance with image augmentation)." @default.
- W2963559171 created "2019-07-30" @default.
- W2963559171 creator A5008456610 @default.
- W2963559171 creator A5053995594 @default.
- W2963559171 date "2016-06-20" @default.
- W2963559171 modified "2023-09-27" @default.
- W2963559171 title "Learning Convolutional Neural Networks using Hybrid Orthogonal Projection and Estimation" @default.
- W2963559171 hasPublicationYear "2016" @default.
- W2963559171 type Work @default.
- W2963559171 sameAs 2963559171 @default.
- W2963559171 citedByCount "3" @default.
- W2963559171 countsByYear W29635591712020 @default.
- W2963559171 countsByYear W29635591712021 @default.
- W2963559171 crossrefType "proceedings-article" @default.
- W2963559171 hasAuthorship W2963559171A5008456610 @default.
- W2963559171 hasAuthorship W2963559171A5053995594 @default.
- W2963559171 hasConcept C11413529 @default.
- W2963559171 hasConcept C114614502 @default.
- W2963559171 hasConcept C138885662 @default.
- W2963559171 hasConcept C153180895 @default.
- W2963559171 hasConcept C154945302 @default.
- W2963559171 hasConcept C17137986 @default.
- W2963559171 hasConcept C202444582 @default.
- W2963559171 hasConcept C2524010 @default.
- W2963559171 hasConcept C2776401178 @default.
- W2963559171 hasConcept C2777210771 @default.
- W2963559171 hasConcept C33676613 @default.
- W2963559171 hasConcept C33923547 @default.
- W2963559171 hasConcept C41008148 @default.
- W2963559171 hasConcept C41895202 @default.
- W2963559171 hasConcept C45347329 @default.
- W2963559171 hasConcept C50644808 @default.
- W2963559171 hasConcept C52622490 @default.
- W2963559171 hasConcept C57493831 @default.
- W2963559171 hasConcept C70437156 @default.
- W2963559171 hasConcept C74193536 @default.
- W2963559171 hasConcept C81363708 @default.
- W2963559171 hasConceptScore W2963559171C11413529 @default.
- W2963559171 hasConceptScore W2963559171C114614502 @default.
- W2963559171 hasConceptScore W2963559171C138885662 @default.
- W2963559171 hasConceptScore W2963559171C153180895 @default.
- W2963559171 hasConceptScore W2963559171C154945302 @default.
- W2963559171 hasConceptScore W2963559171C17137986 @default.
- W2963559171 hasConceptScore W2963559171C202444582 @default.
- W2963559171 hasConceptScore W2963559171C2524010 @default.
- W2963559171 hasConceptScore W2963559171C2776401178 @default.
- W2963559171 hasConceptScore W2963559171C2777210771 @default.
- W2963559171 hasConceptScore W2963559171C33676613 @default.
- W2963559171 hasConceptScore W2963559171C33923547 @default.
- W2963559171 hasConceptScore W2963559171C41008148 @default.
- W2963559171 hasConceptScore W2963559171C41895202 @default.
- W2963559171 hasConceptScore W2963559171C45347329 @default.
- W2963559171 hasConceptScore W2963559171C50644808 @default.
- W2963559171 hasConceptScore W2963559171C52622490 @default.
- W2963559171 hasConceptScore W2963559171C57493831 @default.
- W2963559171 hasConceptScore W2963559171C70437156 @default.
- W2963559171 hasConceptScore W2963559171C74193536 @default.
- W2963559171 hasConceptScore W2963559171C81363708 @default.
- W2963559171 hasLocation W29635591711 @default.
- W2963559171 hasOpenAccess W2963559171 @default.
- W2963559171 hasPrimaryLocation W29635591711 @default.
- W2963559171 hasRelatedWork W2123045220 @default.
- W2963559171 hasRelatedWork W2460512935 @default.
- W2963559171 hasRelatedWork W2599764753 @default.
- W2963559171 hasRelatedWork W2753224637 @default.
- W2963559171 hasRelatedWork W2772031001 @default.
- W2963559171 hasRelatedWork W2809047131 @default.
- W2963559171 hasRelatedWork W2891179104 @default.
- W2963559171 hasRelatedWork W2901800056 @default.
- W2963559171 hasRelatedWork W2903109033 @default.
- W2963559171 hasRelatedWork W2903953509 @default.
- W2963559171 hasRelatedWork W2932481940 @default.
- W2963559171 hasRelatedWork W2963828468 @default.
- W2963559171 hasRelatedWork W2964590182 @default.
- W2963559171 hasRelatedWork W2965485539 @default.
- W2963559171 hasRelatedWork W2969662912 @default.
- W2963559171 hasRelatedWork W2978772012 @default.
- W2963559171 hasRelatedWork W2983993072 @default.
- W2963559171 hasRelatedWork W3020554786 @default.
- W2963559171 hasRelatedWork W3034302069 @default.
- W2963559171 hasRelatedWork W2527636115 @default.
- W2963559171 isParatext "false" @default.
- W2963559171 isRetracted "false" @default.
- W2963559171 magId "2963559171" @default.
- W2963559171 workType "article" @default.