Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208893107> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3208893107 abstract "The interpretability of deep neural networks can serve as reliable guidance for algorithm improvement. By visualizing class-relevant features in the form of heatmap, the Class Activation Map (CAM) and derivative versions have been widely exploited to study the interpretability of softmax-based neural networks. However, CAM cannot be adopted directly for metric learning, because there is no fully-connected layer in metric-learning-based methods. To solve this problem, we propose a Distance-based Class Activation Map (Dist-CAM) in this paper, which can be applied to metric learning directly. Comprehensive experiments are conducted with several convolutional neural networks trained on the ILSVRC 2012 and the result shows that Dist-CAM can achieve better performance than the original CAM in weakly-supervised localization tasks, which means the heatmap generated by Dist-CAM can effectively visualize class-relevant features. Finally, the applications of Dist-CAM on specific tasks, i.e., few-shot learning, image retrieval and re-identification, based on metric learning are presented." @default.
- W3208893107 created "2021-11-08" @default.
- W3208893107 creator A5006236325 @default.
- W3208893107 creator A5028009429 @default.
- W3208893107 creator A5039316678 @default.
- W3208893107 creator A5059058846 @default.
- W3208893107 creator A5062646818 @default.
- W3208893107 date "2021-01-01" @default.
- W3208893107 modified "2023-09-27" @default.
- W3208893107 title "Distance-Based Class Activation Map for Metric Learning" @default.
- W3208893107 cites W2204750386 @default.
- W3208893107 cites W2295107390 @default.
- W3208893107 cites W2511556322 @default.
- W3208893107 cites W2613997951 @default.
- W3208893107 cites W2765793020 @default.
- W3208893107 cites W2892034740 @default.
- W3208893107 cites W2895347732 @default.
- W3208893107 cites W2904949947 @default.
- W3208893107 cites W2953271441 @default.
- W3208893107 cites W2963311325 @default.
- W3208893107 cites W2963466847 @default.
- W3208893107 cites W2963988212 @default.
- W3208893107 cites W2965949912 @default.
- W3208893107 cites W2967515867 @default.
- W3208893107 cites W3102564565 @default.
- W3208893107 cites W3108878460 @default.
- W3208893107 doi "https://doi.org/10.1007/978-3-030-88013-2_28" @default.
- W3208893107 hasPublicationYear "2021" @default.
- W3208893107 type Work @default.
- W3208893107 sameAs 3208893107 @default.
- W3208893107 citedByCount "0" @default.
- W3208893107 crossrefType "book-chapter" @default.
- W3208893107 hasAuthorship W3208893107A5006236325 @default.
- W3208893107 hasAuthorship W3208893107A5028009429 @default.
- W3208893107 hasAuthorship W3208893107A5039316678 @default.
- W3208893107 hasAuthorship W3208893107A5059058846 @default.
- W3208893107 hasAuthorship W3208893107A5062646818 @default.
- W3208893107 hasConcept C108583219 @default.
- W3208893107 hasConcept C119857082 @default.
- W3208893107 hasConcept C153180895 @default.
- W3208893107 hasConcept C154945302 @default.
- W3208893107 hasConcept C162324750 @default.
- W3208893107 hasConcept C176217482 @default.
- W3208893107 hasConcept C188441871 @default.
- W3208893107 hasConcept C21547014 @default.
- W3208893107 hasConcept C2777212361 @default.
- W3208893107 hasConcept C2781067378 @default.
- W3208893107 hasConcept C41008148 @default.
- W3208893107 hasConcept C50644808 @default.
- W3208893107 hasConcept C81363708 @default.
- W3208893107 hasConceptScore W3208893107C108583219 @default.
- W3208893107 hasConceptScore W3208893107C119857082 @default.
- W3208893107 hasConceptScore W3208893107C153180895 @default.
- W3208893107 hasConceptScore W3208893107C154945302 @default.
- W3208893107 hasConceptScore W3208893107C162324750 @default.
- W3208893107 hasConceptScore W3208893107C176217482 @default.
- W3208893107 hasConceptScore W3208893107C188441871 @default.
- W3208893107 hasConceptScore W3208893107C21547014 @default.
- W3208893107 hasConceptScore W3208893107C2777212361 @default.
- W3208893107 hasConceptScore W3208893107C2781067378 @default.
- W3208893107 hasConceptScore W3208893107C41008148 @default.
- W3208893107 hasConceptScore W3208893107C50644808 @default.
- W3208893107 hasConceptScore W3208893107C81363708 @default.
- W3208893107 hasLocation W32088931071 @default.
- W3208893107 hasOpenAccess W3208893107 @default.
- W3208893107 hasPrimaryLocation W32088931071 @default.
- W3208893107 hasRelatedWork W12251780 @default.
- W3208893107 hasRelatedWork W12336802 @default.
- W3208893107 hasRelatedWork W12793662 @default.
- W3208893107 hasRelatedWork W5264008 @default.
- W3208893107 hasRelatedWork W6680660 @default.
- W3208893107 hasRelatedWork W6878516 @default.
- W3208893107 hasRelatedWork W7303821 @default.
- W3208893107 hasRelatedWork W8198582 @default.
- W3208893107 hasRelatedWork W9190101 @default.
- W3208893107 hasRelatedWork W9770290 @default.
- W3208893107 isParatext "false" @default.
- W3208893107 isRetracted "false" @default.
- W3208893107 magId "3208893107" @default.
- W3208893107 workType "book-chapter" @default.