FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891787551> ?p ?o ?g. }

• W2891787551 abstract "Fine-grained image classification aims at recognizing different subordinates in one basic-level category, for example, distinguishing species of birds. Compared with basic-level classification, it has both low inter-class and high intra-class variances. Therefore, utilization of discriminative parts is crucial for fine-grained classification. In this paper, we propose a Gaussian mixture model, which fuses part features by Gaussian mixture layer. More specifically, it first generates a set of part proposals by selective search. Then, we extract image feature maps from mid-layers of convolutional neural networks. Feature maps and part proposals are used for calculating part features via spatial pyramid pooling. Next, Gaussian mixture layer treats part features as data points and uses several Gaussian components to model their distribution. It finds clusters for input and generates output features based on combination of cluster center. Finally, the output feature can represent the whole image and is used for classification. Training process of the model consists of two loops. The outer loop is the optimization of the whole network, and the inner loop is about the EM algorithm used in Gaussian mixture layer. Experiments demonstrate higher or similar performance on four fine-grained data sets compared with the state-of-the-arts. More discussions on Gaussian mixture layer are also provided." @default.
• W2891787551 created "2018-09-27" @default.
• W2891787551 creator A5025657211 @default.
• W2891787551 creator A5029569657 @default.
• W2891787551 creator A5058509635 @default.
• W2891787551 creator A5059644827 @default.
• W2891787551 date "2018-01-01" @default.
• W2891787551 modified "2023-09-24" @default.
• W2891787551 title "Fine-Grained Image Classification With Gaussian Mixture Layer" @default.
• W2891787551 cites W1159302035 @default.
• W2891787551 cites W1496650988 @default.
• W2891787551 cites W1531492214 @default.
• W2891787551 cites W1556540526 @default.
• W2891787551 cites W1616462885 @default.
• W2891787551 cites W1686810756 @default.
• W2891787551 cites W1797268635 @default.
• W2891787551 cites W1846799578 @default.
• W2891787551 cites W1849277567 @default.
• W2891787551 cites W1898560071 @default.
• W2891787551 cites W1905692714 @default.
• W2891787551 cites W1928906481 @default.
• W2891787551 cites W1966385142 @default.
• W2891787551 cites W1980526845 @default.
• W2891787551 cites W1995543189 @default.
• W2891787551 cites W2049633694 @default.
• W2891787551 cites W2064675550 @default.
• W2891787551 cites W2088049833 @default.
• W2891787551 cites W2102605133 @default.
• W2891787551 cites W2102625004 @default.
• W2891787551 cites W2104657103 @default.
• W2891787551 cites W2109255472 @default.
• W2891787551 cites W2110765924 @default.
• W2891787551 cites W2117539524 @default.
• W2891787551 cites W2138011018 @default.
• W2891787551 cites W2151103935 @default.
• W2891787551 cites W2154209944 @default.
• W2891787551 cites W2161160262 @default.
• W2891787551 cites W2161969291 @default.
• W2891787551 cites W2163352848 @default.
• W2891787551 cites W2163605009 @default.
• W2891787551 cites W2169501191 @default.
• W2891787551 cites W2207849498 @default.
• W2891787551 cites W2289708887 @default.
• W2891787551 cites W2337668290 @default.
• W2891787551 cites W2345671296 @default.
• W2891787551 cites W2403585668 @default.
• W2891787551 cites W2462457117 @default.
• W2891787551 cites W2479109623 @default.
• W2891787551 cites W2554320282 @default.
• W2891787551 cites W2586661295 @default.
• W2891787551 cites W2604134068 @default.
• W2891787551 cites W2604702198 @default.
• W2891787551 cites W2604710550 @default.
• W2891787551 cites W2737725206 @default.
• W2891787551 cites W2740620254 @default.
• W2891787551 cites W2741910023 @default.
• W2891787551 cites W2746834958 @default.
• W2891787551 cites W2765268259 @default.
• W2891787551 cites W2773003563 @default.
• W2891787551 cites W2780838211 @default.
• W2891787551 cites W2785994986 @default.
• W2891787551 cites W2785996189 @default.
• W2891787551 cites W2890715498 @default.
• W2891787551 cites W2899771611 @default.
• W2891787551 cites W2919115771 @default.
• W2891787551 cites W2949650786 @default.
• W2891787551 cites W2964176323 @default.
• W2891787551 cites W2964275061 @default.
• W2891787551 cites W3103844505 @default.
• W2891787551 cites W56385144 @default.
• W2891787551 doi "https://doi.org/10.1109/access.2018.2871621" @default.
• W2891787551 hasPublicationYear "2018" @default.
• W2891787551 type Work @default.
• W2891787551 sameAs 2891787551 @default.
• W2891787551 citedByCount "7" @default.
• W2891787551 countsByYear W28917875512019 @default.
• W2891787551 countsByYear W28917875512020 @default.
• W2891787551 crossrefType "journal-article" @default.
• W2891787551 hasAuthorship W2891787551A5025657211 @default.
• W2891787551 hasAuthorship W2891787551A5029569657 @default.
• W2891787551 hasAuthorship W2891787551A5058509635 @default.
• W2891787551 hasAuthorship W2891787551A5059644827 @default.
• W2891787551 hasBestOaLocation W28917875511 @default.
• W2891787551 hasConcept C115961682 @default.
• W2891787551 hasConcept C121332964 @default.
• W2891787551 hasConcept C138885662 @default.
• W2891787551 hasConcept C142575187 @default.
• W2891787551 hasConcept C153180895 @default.
• W2891787551 hasConcept C154945302 @default.
• W2891787551 hasConcept C163716315 @default.
• W2891787551 hasConcept C2524010 @default.
• W2891787551 hasConcept C2776401178 @default.
• W2891787551 hasConcept C33923547 @default.
• W2891787551 hasConcept C41008148 @default.
• W2891787551 hasConcept C41895202 @default.
• W2891787551 hasConcept C52622490 @default.
• W2891787551 hasConcept C61224824 @default.
• W2891787551 hasConcept C61326573 @default.
• W2891787551 hasConcept C62520636 @default.
• W2891787551 hasConcept C70437156 @default.

• next