Matches in SemOpenAlex for { <https://semopenalex.org/work/W3196967073> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3196967073 endingPage "7607" @default.
- W3196967073 startingPage "7593" @default.
- W3196967073 abstract "This work explores the visual explanation for deep metric learning and its applications. As an important problem for learning representation, metric learning has attracted much attention recently, while the interpretation of the metric learning model is not as well-studied as classification. To this end, we propose an intuitive idea to show where contributes the most to the overall similarity of two input images by decomposing the final activation. Instead of only providing the overall activation map of each image, we propose to generate point-to-point activation intensity between two images so that the relationship between different regions is uncovered. We show that the proposed framework can be directly applied to a wide range of metric learning applications and provides valuable information for model understanding. Both theoretical and empirical analyses are provided to demonstrate the superiority of the proposed overall activation map over existing methods. Furthermore, our experiments validate the effectiveness of the proposed point-specific activation map on two applications, i.e. cross-view pattern discovery and interactive retrieval. Code is available at https://github.com/Jeff-Zilence/Explain_Metric_Learning" @default.
- W3196967073 created "2021-09-13" @default.
- W3196967073 creator A5009793780 @default.
- W3196967073 creator A5024530392 @default.
- W3196967073 creator A5068650938 @default.
- W3196967073 date "2021-01-01" @default.
- W3196967073 modified "2023-09-24" @default.
- W3196967073 title "Visual Explanation for Deep Metric Learning" @default.
- W3196967073 cites W1915485278 @default.
- W3196967073 cites W2157364932 @default.
- W3196967073 cites W2204750386 @default.
- W3196967073 cites W2295107390 @default.
- W3196967073 cites W2470394683 @default.
- W3196967073 cites W2572697301 @default.
- W3196967073 cites W2598199894 @default.
- W3196967073 cites W2744926832 @default.
- W3196967073 cites W2765793020 @default.
- W3196967073 cites W2776207810 @default.
- W3196967073 cites W2797200251 @default.
- W3196967073 cites W2799087793 @default.
- W3196967073 cites W2895739182 @default.
- W3196967073 cites W2954765307 @default.
- W3196967073 cites W2962858109 @default.
- W3196967073 cites W2962898354 @default.
- W3196967073 cites W2962923976 @default.
- W3196967073 cites W2963026686 @default.
- W3196967073 cites W2963081790 @default.
- W3196967073 cites W2963466847 @default.
- W3196967073 cites W2963953476 @default.
- W3196967073 cites W2964271799 @default.
- W3196967073 cites W2967515867 @default.
- W3196967073 cites W2969985801 @default.
- W3196967073 cites W2998792609 @default.
- W3196967073 cites W3022730539 @default.
- W3196967073 cites W3033235266 @default.
- W3196967073 cites W3035314413 @default.
- W3196967073 cites W3035673257 @default.
- W3196967073 cites W3047363187 @default.
- W3196967073 cites W3099206234 @default.
- W3196967073 cites W3101609372 @default.
- W3196967073 doi "https://doi.org/10.1109/tip.2021.3107214" @default.
- W3196967073 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34469296" @default.
- W3196967073 hasPublicationYear "2021" @default.
- W3196967073 type Work @default.
- W3196967073 sameAs 3196967073 @default.
- W3196967073 citedByCount "6" @default.
- W3196967073 countsByYear W31969670732022 @default.
- W3196967073 countsByYear W31969670732023 @default.
- W3196967073 crossrefType "journal-article" @default.
- W3196967073 hasAuthorship W3196967073A5009793780 @default.
- W3196967073 hasAuthorship W3196967073A5024530392 @default.
- W3196967073 hasAuthorship W3196967073A5068650938 @default.
- W3196967073 hasBestOaLocation W31969670731 @default.
- W3196967073 hasConcept C153180895 @default.
- W3196967073 hasConcept C154945302 @default.
- W3196967073 hasConcept C162324750 @default.
- W3196967073 hasConcept C176217482 @default.
- W3196967073 hasConcept C21547014 @default.
- W3196967073 hasConcept C31972630 @default.
- W3196967073 hasConcept C36464697 @default.
- W3196967073 hasConcept C41008148 @default.
- W3196967073 hasConceptScore W3196967073C153180895 @default.
- W3196967073 hasConceptScore W3196967073C154945302 @default.
- W3196967073 hasConceptScore W3196967073C162324750 @default.
- W3196967073 hasConceptScore W3196967073C176217482 @default.
- W3196967073 hasConceptScore W3196967073C21547014 @default.
- W3196967073 hasConceptScore W3196967073C31972630 @default.
- W3196967073 hasConceptScore W3196967073C36464697 @default.
- W3196967073 hasConceptScore W3196967073C41008148 @default.
- W3196967073 hasFunder F4320306076 @default.
- W3196967073 hasLocation W31969670731 @default.
- W3196967073 hasLocation W31969670732 @default.
- W3196967073 hasOpenAccess W3196967073 @default.
- W3196967073 hasPrimaryLocation W31969670731 @default.
- W3196967073 hasRelatedWork W1891287906 @default.
- W3196967073 hasRelatedWork W1969923398 @default.
- W3196967073 hasRelatedWork W2036807459 @default.
- W3196967073 hasRelatedWork W2073454628 @default.
- W3196967073 hasRelatedWork W2139746023 @default.
- W3196967073 hasRelatedWork W2229312674 @default.
- W3196967073 hasRelatedWork W2755342338 @default.
- W3196967073 hasRelatedWork W2772917594 @default.
- W3196967073 hasRelatedWork W3090091644 @default.
- W3196967073 hasRelatedWork W4286783870 @default.
- W3196967073 hasVolume "30" @default.
- W3196967073 isParatext "false" @default.
- W3196967073 isRetracted "false" @default.
- W3196967073 magId "3196967073" @default.
- W3196967073 workType "article" @default.