Matches in SemOpenAlex for { <https://semopenalex.org/work/W3115684014> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3115684014 abstract "With the rise of Convolutional Neural Network (CNN) in the recent years, image classification has shown outstanding performances in the computer vision field. Many wellknown state of the art's CNN architectures such as the ResNet family are applying a Global Average Pooling (GAP) to reduce the number of parameters of the fully connected layers. Most of the time, this pooling operation helps to prevent overfitting but we claim that it has a serious weakness for specific images where small details are crucial to predict their category, such as material images. In this case, the details are lost in the global average, providing non accurate global features. In this paper, we propose to select the most important local features before applying the GAP. In this aim, we add a branch in the classification network that predicts the confidence the network should have in each local feature vector. The less confident features are filtered out before applying the GAP. Experimental results on three datasets show that our approach outperforms recent alternatives in terms of classification accuracy and output probability calibration." @default.
- W3115684014 created "2021-01-05" @default.
- W3115684014 creator A5005318650 @default.
- W3115684014 creator A5025451778 @default.
- W3115684014 creator A5041689611 @default.
- W3115684014 creator A5060353395 @default.
- W3115684014 date "2020-11-25" @default.
- W3115684014 modified "2023-10-18" @default.
- W3115684014 title "Confidence-based Local Feature Selection for Material Classification" @default.
- W3115684014 cites W1909952827 @default.
- W3115684014 cites W2037131007 @default.
- W3115684014 cites W2108598243 @default.
- W3115684014 cites W2153786187 @default.
- W3115684014 cites W2194775991 @default.
- W3115684014 cites W2513285095 @default.
- W3115684014 cites W2566365295 @default.
- W3115684014 cites W2780661351 @default.
- W3115684014 cites W2951019013 @default.
- W3115684014 cites W2956371155 @default.
- W3115684014 cites W2963190516 @default.
- W3115684014 cites W2963239066 @default.
- W3115684014 cites W2963828468 @default.
- W3115684014 doi "https://doi.org/10.1109/ivcnz51579.2020.9290612" @default.
- W3115684014 hasPublicationYear "2020" @default.
- W3115684014 type Work @default.
- W3115684014 sameAs 3115684014 @default.
- W3115684014 citedByCount "1" @default.
- W3115684014 countsByYear W31156840142023 @default.
- W3115684014 crossrefType "proceedings-article" @default.
- W3115684014 hasAuthorship W3115684014A5005318650 @default.
- W3115684014 hasAuthorship W3115684014A5025451778 @default.
- W3115684014 hasAuthorship W3115684014A5041689611 @default.
- W3115684014 hasAuthorship W3115684014A5060353395 @default.
- W3115684014 hasConcept C115961682 @default.
- W3115684014 hasConcept C119857082 @default.
- W3115684014 hasConcept C138885662 @default.
- W3115684014 hasConcept C148483581 @default.
- W3115684014 hasConcept C153180895 @default.
- W3115684014 hasConcept C154945302 @default.
- W3115684014 hasConcept C202444582 @default.
- W3115684014 hasConcept C22019652 @default.
- W3115684014 hasConcept C2776401178 @default.
- W3115684014 hasConcept C33923547 @default.
- W3115684014 hasConcept C41008148 @default.
- W3115684014 hasConcept C41895202 @default.
- W3115684014 hasConcept C50644808 @default.
- W3115684014 hasConcept C70437156 @default.
- W3115684014 hasConcept C75294576 @default.
- W3115684014 hasConcept C81363708 @default.
- W3115684014 hasConcept C81917197 @default.
- W3115684014 hasConcept C9652623 @default.
- W3115684014 hasConceptScore W3115684014C115961682 @default.
- W3115684014 hasConceptScore W3115684014C119857082 @default.
- W3115684014 hasConceptScore W3115684014C138885662 @default.
- W3115684014 hasConceptScore W3115684014C148483581 @default.
- W3115684014 hasConceptScore W3115684014C153180895 @default.
- W3115684014 hasConceptScore W3115684014C154945302 @default.
- W3115684014 hasConceptScore W3115684014C202444582 @default.
- W3115684014 hasConceptScore W3115684014C22019652 @default.
- W3115684014 hasConceptScore W3115684014C2776401178 @default.
- W3115684014 hasConceptScore W3115684014C33923547 @default.
- W3115684014 hasConceptScore W3115684014C41008148 @default.
- W3115684014 hasConceptScore W3115684014C41895202 @default.
- W3115684014 hasConceptScore W3115684014C50644808 @default.
- W3115684014 hasConceptScore W3115684014C70437156 @default.
- W3115684014 hasConceptScore W3115684014C75294576 @default.
- W3115684014 hasConceptScore W3115684014C81363708 @default.
- W3115684014 hasConceptScore W3115684014C81917197 @default.
- W3115684014 hasConceptScore W3115684014C9652623 @default.
- W3115684014 hasLocation W31156840141 @default.
- W3115684014 hasOpenAccess W3115684014 @default.
- W3115684014 hasPrimaryLocation W31156840141 @default.
- W3115684014 hasRelatedWork W2760085659 @default.
- W3115684014 hasRelatedWork W2940661641 @default.
- W3115684014 hasRelatedWork W2969680539 @default.
- W3115684014 hasRelatedWork W3013138473 @default.
- W3115684014 hasRelatedWork W3036126916 @default.
- W3115684014 hasRelatedWork W4220996320 @default.
- W3115684014 hasRelatedWork W4283454150 @default.
- W3115684014 hasRelatedWork W4295514622 @default.
- W3115684014 hasRelatedWork W4317374280 @default.
- W3115684014 hasRelatedWork W785854688 @default.
- W3115684014 isParatext "false" @default.
- W3115684014 isRetracted "false" @default.
- W3115684014 magId "3115684014" @default.
- W3115684014 workType "article" @default.