FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891409152> ?p ?o ?g. }

• W2891409152 endingPage "44280" @default.
• W2891409152 startingPage "44268" @default.
• W2891409152 abstract "Semantic-based image retrieval plays an important role in many practical applications, which aims to look for images with similar contents. Extracting discriminative representations of images is the real crux of this task. Directly utilizing the results of fully connected layers of convolutional neural networks (CNNs) is one of the best feature extraction methods. However, the fully connected layer is only supervised by the softmax loss, which only aims to maximize the accuracy of object classification and hardly pays attention to the spatial distribution of features, especially the intra-class and inter-class feature distances which are of great importance in semantic-based image retrieval. To compensate the performance degradation due to this reason, we try to address the spatial distribution of the features by two different loss functions. The first loss function jointly combines the softmax loss and the center loss in the training of the CNNs, which simultaneously ensures that the features of images with different contents are separable and the features of images in the same class are close. The second loss function is defined as an improved center loss which not only penalizes the distance between the obtained deep feature and the feature center of its own class, but also encourages a far distance between the feature and the feature centers of any other classes. We have conducted experiments on both ILSVRC data set and Caltech256 data set, demonstrated that the deep features got by our approaches can achieve better performance than other methods in semantic-based image retrieval, and the improved center loss can further outperform the joint supervision of the softmax loss and the center loss." @default.
• W2891409152 created "2018-09-27" @default.
• W2891409152 creator A5007719477 @default.
• W2891409152 creator A5034808877 @default.
• W2891409152 creator A5035760915 @default.
• W2891409152 creator A5077109430 @default.
• W2891409152 creator A5078547624 @default.
• W2891409152 date "2018-01-01" @default.
• W2891409152 modified "2023-10-16" @default.
• W2891409152 title "Discriminative Deep Feature Learning for Semantic-Based Image Retrieval" @default.
• W2891409152 cites W1566135517 @default.
• W2891409152 cites W1969732194 @default.
• W2891409152 cites W1974647172 @default.
• W2891409152 cites W2011589513 @default.
• W2891409152 cites W2028684662 @default.
• W2891409152 cites W2036718463 @default.
• W2891409152 cites W2046766629 @default.
• W2891409152 cites W2053695737 @default.
• W2891409152 cites W2081712564 @default.
• W2891409152 cites W2084910432 @default.
• W2891409152 cites W2091753323 @default.
• W2891409152 cites W2097117768 @default.
• W2891409152 cites W2107925163 @default.
• W2891409152 cites W2108598243 @default.
• W2891409152 cites W2112464244 @default.
• W2891409152 cites W2112796928 @default.
• W2891409152 cites W2113855951 @default.
• W2891409152 cites W2117539524 @default.
• W2891409152 cites W2118509786 @default.
• W2891409152 cites W2123229215 @default.
• W2891409152 cites W2124386111 @default.
• W2891409152 cites W2125148312 @default.
• W2891409152 cites W2130660124 @default.
• W2891409152 cites W2137183034 @default.
• W2891409152 cites W2144502914 @default.
• W2891409152 cites W2147069236 @default.
• W2891409152 cites W2147277317 @default.
• W2891409152 cites W2157364932 @default.
• W2891409152 cites W2161969291 @default.
• W2891409152 cites W2162915993 @default.
• W2891409152 cites W2163352848 @default.
• W2891409152 cites W2164524945 @default.
• W2891409152 cites W2168356304 @default.
• W2891409152 cites W2194775991 @default.
• W2891409152 cites W2733548594 @default.
• W2891409152 cites W3099206234 @default.
• W2891409152 doi "https://doi.org/10.1109/access.2018.2862464" @default.
• W2891409152 hasPublicationYear "2018" @default.
• W2891409152 type Work @default.
• W2891409152 sameAs 2891409152 @default.
• W2891409152 citedByCount "18" @default.
• W2891409152 countsByYear W28914091522019 @default.
• W2891409152 countsByYear W28914091522020 @default.
• W2891409152 countsByYear W28914091522021 @default.
• W2891409152 countsByYear W28914091522022 @default.
• W2891409152 crossrefType "journal-article" @default.
• W2891409152 hasAuthorship W2891409152A5007719477 @default.
• W2891409152 hasAuthorship W2891409152A5034808877 @default.
• W2891409152 hasAuthorship W2891409152A5035760915 @default.
• W2891409152 hasAuthorship W2891409152A5077109430 @default.
• W2891409152 hasAuthorship W2891409152A5078547624 @default.
• W2891409152 hasBestOaLocation W28914091521 @default.
• W2891409152 hasConcept C108583219 @default.
• W2891409152 hasConcept C115961682 @default.
• W2891409152 hasConcept C138885662 @default.
• W2891409152 hasConcept C153180895 @default.
• W2891409152 hasConcept C154945302 @default.
• W2891409152 hasConcept C1667742 @default.
• W2891409152 hasConcept C204321447 @default.
• W2891409152 hasConcept C2776401178 @default.
• W2891409152 hasConcept C2781122975 @default.
• W2891409152 hasConcept C41008148 @default.
• W2891409152 hasConcept C41895202 @default.
• W2891409152 hasConcept C52622490 @default.
• W2891409152 hasConcept C59404180 @default.
• W2891409152 hasConcept C97931131 @default.
• W2891409152 hasConceptScore W2891409152C108583219 @default.
• W2891409152 hasConceptScore W2891409152C115961682 @default.
• W2891409152 hasConceptScore W2891409152C138885662 @default.
• W2891409152 hasConceptScore W2891409152C153180895 @default.
• W2891409152 hasConceptScore W2891409152C154945302 @default.
• W2891409152 hasConceptScore W2891409152C1667742 @default.
• W2891409152 hasConceptScore W2891409152C204321447 @default.
• W2891409152 hasConceptScore W2891409152C2776401178 @default.
• W2891409152 hasConceptScore W2891409152C2781122975 @default.
• W2891409152 hasConceptScore W2891409152C41008148 @default.
• W2891409152 hasConceptScore W2891409152C41895202 @default.
• W2891409152 hasConceptScore W2891409152C52622490 @default.
• W2891409152 hasConceptScore W2891409152C59404180 @default.
• W2891409152 hasConceptScore W2891409152C97931131 @default.
• W2891409152 hasFunder F4320321001 @default.
• W2891409152 hasFunder F4320335777 @default.
• W2891409152 hasLocation W28914091521 @default.
• W2891409152 hasOpenAccess W2891409152 @default.
• W2891409152 hasPrimaryLocation W28914091521 @default.
• W2891409152 hasRelatedWork W2404514746 @default.
• W2891409152 hasRelatedWork W2732542196 @default.
• W2891409152 hasRelatedWork W2743258233 @default.

• next