Matches in SemOpenAlex for { <https://semopenalex.org/work/W2983135586> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2983135586 abstract "With the advances of convolutional neural networks (CNNs), the accuracy of remote sensing image scene classification has been greatly boosted thanks to the powerful features extracted through CNNs. Although significant success has been achieved, most of existing methods are dominated by the use of fully-connected CNN features. This paper focuses on the performance comparison of two kinds of novel pooling strategies, including generalized max pooling (GMP) and taskdriven pooling (TDP), for remote sensing image scene classification. To this end, an off-the-shelf CNN model is used as backbone network to extract multi-scale convolutional features. Then, GMP and TDP are respectively adopted to obtain globally pooled features. Finally, scene classification is performed with support vector machine (SVM). In the experiment, we evaluate the performance of these two kinds of pooling schemes on a widely-used scene classification benchmark data set. The experimental results show that (i) using pooled CNN convolutional features can obtain better results than using fully-connected CNN features and (ii) TDP is slightly better than GMP." @default.
- W2983135586 created "2019-11-22" @default.
- W2983135586 creator A5000359310 @default.
- W2983135586 creator A5012529382 @default.
- W2983135586 creator A5017535979 @default.
- W2983135586 creator A5047940298 @default.
- W2983135586 creator A5049629716 @default.
- W2983135586 creator A5080476856 @default.
- W2983135586 date "2019-07-01" @default.
- W2983135586 modified "2023-10-16" @default.
- W2983135586 title "Performance Comparison of Two Pooling Strategies for Remote Sensing Image Scene Classification" @default.
- W2983135586 cites W1576332977 @default.
- W2983135586 cites W1963500125 @default.
- W2983135586 cites W1977617632 @default.
- W2983135586 cites W1982067089 @default.
- W2983135586 cites W2197216118 @default.
- W2983135586 cites W2291068538 @default.
- W2983135586 cites W2342880667 @default.
- W2983135586 cites W2347115704 @default.
- W2983135586 cites W2512351403 @default.
- W2983135586 cites W2607558879 @default.
- W2983135586 cites W2620429297 @default.
- W2983135586 cites W2620858446 @default.
- W2983135586 cites W2727875856 @default.
- W2983135586 cites W2744582969 @default.
- W2983135586 cites W2783165089 @default.
- W2983135586 cites W2888527098 @default.
- W2983135586 cites W3103856189 @default.
- W2983135586 cites W3105577662 @default.
- W2983135586 doi "https://doi.org/10.1109/igarss.2019.8899877" @default.
- W2983135586 hasPublicationYear "2019" @default.
- W2983135586 type Work @default.
- W2983135586 sameAs 2983135586 @default.
- W2983135586 citedByCount "1" @default.
- W2983135586 countsByYear W29831355862023 @default.
- W2983135586 crossrefType "proceedings-article" @default.
- W2983135586 hasAuthorship W2983135586A5000359310 @default.
- W2983135586 hasAuthorship W2983135586A5012529382 @default.
- W2983135586 hasAuthorship W2983135586A5017535979 @default.
- W2983135586 hasAuthorship W2983135586A5047940298 @default.
- W2983135586 hasAuthorship W2983135586A5049629716 @default.
- W2983135586 hasAuthorship W2983135586A5080476856 @default.
- W2983135586 hasConcept C115961682 @default.
- W2983135586 hasConcept C12267149 @default.
- W2983135586 hasConcept C153180895 @default.
- W2983135586 hasConcept C154945302 @default.
- W2983135586 hasConcept C177264268 @default.
- W2983135586 hasConcept C185798385 @default.
- W2983135586 hasConcept C199360897 @default.
- W2983135586 hasConcept C205649164 @default.
- W2983135586 hasConcept C41008148 @default.
- W2983135586 hasConcept C52622490 @default.
- W2983135586 hasConcept C58489278 @default.
- W2983135586 hasConcept C58640448 @default.
- W2983135586 hasConcept C70437156 @default.
- W2983135586 hasConcept C75294576 @default.
- W2983135586 hasConcept C81363708 @default.
- W2983135586 hasConceptScore W2983135586C115961682 @default.
- W2983135586 hasConceptScore W2983135586C12267149 @default.
- W2983135586 hasConceptScore W2983135586C153180895 @default.
- W2983135586 hasConceptScore W2983135586C154945302 @default.
- W2983135586 hasConceptScore W2983135586C177264268 @default.
- W2983135586 hasConceptScore W2983135586C185798385 @default.
- W2983135586 hasConceptScore W2983135586C199360897 @default.
- W2983135586 hasConceptScore W2983135586C205649164 @default.
- W2983135586 hasConceptScore W2983135586C41008148 @default.
- W2983135586 hasConceptScore W2983135586C52622490 @default.
- W2983135586 hasConceptScore W2983135586C58489278 @default.
- W2983135586 hasConceptScore W2983135586C58640448 @default.
- W2983135586 hasConceptScore W2983135586C70437156 @default.
- W2983135586 hasConceptScore W2983135586C75294576 @default.
- W2983135586 hasConceptScore W2983135586C81363708 @default.
- W2983135586 hasLocation W29831355861 @default.
- W2983135586 hasOpenAccess W2983135586 @default.
- W2983135586 hasPrimaryLocation W29831355861 @default.
- W2983135586 hasRelatedWork W2291847203 @default.
- W2983135586 hasRelatedWork W2514274290 @default.
- W2983135586 hasRelatedWork W2732542196 @default.
- W2983135586 hasRelatedWork W2767651786 @default.
- W2983135586 hasRelatedWork W2769836096 @default.
- W2983135586 hasRelatedWork W2940661641 @default.
- W2983135586 hasRelatedWork W2940977206 @default.
- W2983135586 hasRelatedWork W2969680539 @default.
- W2983135586 hasRelatedWork W3120332919 @default.
- W2983135586 hasRelatedWork W3156786002 @default.
- W2983135586 isParatext "false" @default.
- W2983135586 isRetracted "false" @default.
- W2983135586 magId "2983135586" @default.
- W2983135586 workType "article" @default.