Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912042463> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2912042463 endingPage "219" @default.
- W2912042463 startingPage "210" @default.
- W2912042463 abstract "Abstract Deep metric learning methods aim to transform data features from original scattered space to a discriminative subspace in an end-to-end way, and they have shown promising results on wide applications. Triplet loss functions are the most popular models to tackle deep metric learning problem as they simultaneously enhance separability between different classes and compactness of each class in the embedded subspace. Therefore, effective triplets selection is crucial to the classification performance. However, most of these methods only focus on mining hard negative pairs, which refer to the nearest sample pairs of different classes, while fail to take subtle cluster structure of each class into consideration. To take such information into the metric learning model, a novel scheme based on subtype fuzzy clustering is proposed in this paper. By defining a new clustering degree, we conduct fuzzy clustering for each class to mine classification-oriented subtype structure. The new clustering degree is inversely proportional to the pairwise distance, thus, we can choose the positive pairs of the highest clustering degrees directly based on the farthest distances within each class. This new sampling approach avoids off-line clustering step, for which the network weights update procedure has to be temporarily paused. In other words, our method builds positive pairs without explicit clustering degree computation or off-line clustering. Our method inputs the selected positive pairs and negative pairs into the standard triplet loss to achieve network feature learning. Experimental results show competitive metric learning performance on three benchmark datasets." @default.
- W2912042463 created "2019-02-21" @default.
- W2912042463 creator A5017711576 @default.
- W2912042463 creator A5020478086 @default.
- W2912042463 creator A5034476586 @default.
- W2912042463 creator A5043031658 @default.
- W2912042463 date "2019-06-01" @default.
- W2912042463 modified "2023-10-17" @default.
- W2912042463 title "Deep metric learning via subtype fuzzy clustering" @default.
- W2912042463 cites W1998594584 @default.
- W2912042463 cites W2053677366 @default.
- W2912042463 cites W2062112832 @default.
- W2912042463 cites W2065675334 @default.
- W2912042463 cites W2353169560 @default.
- W2912042463 cites W2592683830 @default.
- W2912042463 cites W2594767544 @default.
- W2912042463 cites W2600889608 @default.
- W2912042463 cites W2622202994 @default.
- W2912042463 cites W2758388116 @default.
- W2912042463 cites W2767014173 @default.
- W2912042463 cites W2772637627 @default.
- W2912042463 cites W617369035 @default.
- W2912042463 doi "https://doi.org/10.1016/j.patcog.2019.01.037" @default.
- W2912042463 hasPublicationYear "2019" @default.
- W2912042463 type Work @default.
- W2912042463 sameAs 2912042463 @default.
- W2912042463 citedByCount "7" @default.
- W2912042463 countsByYear W29120424632019 @default.
- W2912042463 countsByYear W29120424632020 @default.
- W2912042463 countsByYear W29120424632022 @default.
- W2912042463 crossrefType "journal-article" @default.
- W2912042463 hasAuthorship W2912042463A5017711576 @default.
- W2912042463 hasAuthorship W2912042463A5020478086 @default.
- W2912042463 hasAuthorship W2912042463A5034476586 @default.
- W2912042463 hasAuthorship W2912042463A5043031658 @default.
- W2912042463 hasConcept C119857082 @default.
- W2912042463 hasConcept C127413603 @default.
- W2912042463 hasConcept C153180895 @default.
- W2912042463 hasConcept C154945302 @default.
- W2912042463 hasConcept C17212007 @default.
- W2912042463 hasConcept C176217482 @default.
- W2912042463 hasConcept C21547014 @default.
- W2912042463 hasConcept C33923547 @default.
- W2912042463 hasConcept C41008148 @default.
- W2912042463 hasConcept C58166 @default.
- W2912042463 hasConcept C73555534 @default.
- W2912042463 hasConceptScore W2912042463C119857082 @default.
- W2912042463 hasConceptScore W2912042463C127413603 @default.
- W2912042463 hasConceptScore W2912042463C153180895 @default.
- W2912042463 hasConceptScore W2912042463C154945302 @default.
- W2912042463 hasConceptScore W2912042463C17212007 @default.
- W2912042463 hasConceptScore W2912042463C176217482 @default.
- W2912042463 hasConceptScore W2912042463C21547014 @default.
- W2912042463 hasConceptScore W2912042463C33923547 @default.
- W2912042463 hasConceptScore W2912042463C41008148 @default.
- W2912042463 hasConceptScore W2912042463C58166 @default.
- W2912042463 hasConceptScore W2912042463C73555534 @default.
- W2912042463 hasFunder F4320321001 @default.
- W2912042463 hasLocation W29120424631 @default.
- W2912042463 hasOpenAccess W2912042463 @default.
- W2912042463 hasPrimaryLocation W29120424631 @default.
- W2912042463 hasRelatedWork W2006684151 @default.
- W2912042463 hasRelatedWork W2006722563 @default.
- W2912042463 hasRelatedWork W2126150009 @default.
- W2912042463 hasRelatedWork W2130349744 @default.
- W2912042463 hasRelatedWork W2154953197 @default.
- W2912042463 hasRelatedWork W2171530835 @default.
- W2912042463 hasRelatedWork W2294768296 @default.
- W2912042463 hasRelatedWork W2782343467 @default.
- W2912042463 hasRelatedWork W3123285233 @default.
- W2912042463 hasRelatedWork W2564101421 @default.
- W2912042463 hasVolume "90" @default.
- W2912042463 isParatext "false" @default.
- W2912042463 isRetracted "false" @default.
- W2912042463 magId "2912042463" @default.
- W2912042463 workType "article" @default.