Matches in SemOpenAlex for { <https://semopenalex.org/work/W2975186974> ?p ?o ?g. }
- W2975186974 abstract "Metric learning seeks to embed images of objects suchthat class-defined relations are captured by the embeddingspace. However, variability in images is not just due to different depicted object classes, but also depends on other latent characteristics such as viewpoint or illumination. In addition to these structured properties, random noise further obstructs the visual relations of interest. The common approach to metric learning is to enforce a representation that is invariant under all factors but the ones of interest. In contrast, we propose to explicitly learn the latent characteristics that are shared by and go across object classes. We can then directly explain away structured visual variability, rather than assuming it to be unknown random noise. We propose a novel surrogate task to learn visual characteristics shared across classes with a separate encoder. This encoder is trained jointly with the encoder for class information by reducing their mutual information. On five standard image retrieval benchmarks the approach significantly improves upon the state-of-the-art." @default.
- W2975186974 created "2019-10-03" @default.
- W2975186974 creator A5066554507 @default.
- W2975186974 creator A5074576698 @default.
- W2975186974 creator A5084415727 @default.
- W2975186974 date "2019-09-25" @default.
- W2975186974 modified "2023-09-26" @default.
- W2975186974 title "MIC: Mining Interclass Characteristics for Improved Metric Learning" @default.
- W2975186974 cites W1522301498 @default.
- W2975186974 cites W1532325895 @default.
- W2975186974 cites W1731081199 @default.
- W2975186974 cites W1797268635 @default.
- W2975186974 cites W1988790447 @default.
- W2975186974 cites W2124509324 @default.
- W2975186974 cites W2138011018 @default.
- W2975186974 cites W2157364932 @default.
- W2975186974 cites W2194775991 @default.
- W2975186974 cites W2321533354 @default.
- W2975186974 cites W2470322391 @default.
- W2975186974 cites W2471768434 @default.
- W2975186974 cites W2547446130 @default.
- W2975186974 cites W2549858646 @default.
- W2975186974 cites W2593864460 @default.
- W2975186974 cites W2605102252 @default.
- W2975186974 cites W2606611007 @default.
- W2975186974 cites W2613997951 @default.
- W2975186974 cites W2745436507 @default.
- W2975186974 cites W2779066530 @default.
- W2975186974 cites W2786672974 @default.
- W2975186974 cites W2798303923 @default.
- W2975186974 cites W2883725317 @default.
- W2975186974 cites W2885563408 @default.
- W2975186974 cites W2895115565 @default.
- W2975186974 cites W2895347732 @default.
- W2975186974 cites W2895608766 @default.
- W2975186974 cites W2899771611 @default.
- W2975186974 cites W2948077755 @default.
- W2975186974 cites W2962877362 @default.
- W2975186974 cites W2962931121 @default.
- W2975186974 cites W2963026686 @default.
- W2975186974 cites W2963113119 @default.
- W2975186974 cites W2963350250 @default.
- W2975186974 cites W2963465221 @default.
- W2975186974 cites W2963740830 @default.
- W2975186974 cites W2963925503 @default.
- W2975186974 cites W2963988212 @default.
- W2975186974 cites W2964178561 @default.
- W2975186974 cites W603908379 @default.
- W2975186974 hasPublicationYear "2019" @default.
- W2975186974 type Work @default.
- W2975186974 sameAs 2975186974 @default.
- W2975186974 citedByCount "7" @default.
- W2975186974 countsByYear W29751869742019 @default.
- W2975186974 countsByYear W29751869742020 @default.
- W2975186974 countsByYear W29751869742021 @default.
- W2975186974 countsByYear W29751869742022 @default.
- W2975186974 crossrefType "posted-content" @default.
- W2975186974 hasAuthorship W2975186974A5066554507 @default.
- W2975186974 hasAuthorship W2975186974A5074576698 @default.
- W2975186974 hasAuthorship W2975186974A5084415727 @default.
- W2975186974 hasConcept C111919701 @default.
- W2975186974 hasConcept C118505674 @default.
- W2975186974 hasConcept C119857082 @default.
- W2975186974 hasConcept C152139883 @default.
- W2975186974 hasConcept C153180895 @default.
- W2975186974 hasConcept C154945302 @default.
- W2975186974 hasConcept C162324750 @default.
- W2975186974 hasConcept C176217482 @default.
- W2975186974 hasConcept C17744445 @default.
- W2975186974 hasConcept C190470478 @default.
- W2975186974 hasConcept C199539241 @default.
- W2975186974 hasConcept C202444582 @default.
- W2975186974 hasConcept C21547014 @default.
- W2975186974 hasConcept C2776359362 @default.
- W2975186974 hasConcept C2776502983 @default.
- W2975186974 hasConcept C2777212361 @default.
- W2975186974 hasConcept C2780012671 @default.
- W2975186974 hasConcept C2781238097 @default.
- W2975186974 hasConcept C33923547 @default.
- W2975186974 hasConcept C36464697 @default.
- W2975186974 hasConcept C37914503 @default.
- W2975186974 hasConcept C41008148 @default.
- W2975186974 hasConcept C94625758 @default.
- W2975186974 hasConceptScore W2975186974C111919701 @default.
- W2975186974 hasConceptScore W2975186974C118505674 @default.
- W2975186974 hasConceptScore W2975186974C119857082 @default.
- W2975186974 hasConceptScore W2975186974C152139883 @default.
- W2975186974 hasConceptScore W2975186974C153180895 @default.
- W2975186974 hasConceptScore W2975186974C154945302 @default.
- W2975186974 hasConceptScore W2975186974C162324750 @default.
- W2975186974 hasConceptScore W2975186974C176217482 @default.
- W2975186974 hasConceptScore W2975186974C17744445 @default.
- W2975186974 hasConceptScore W2975186974C190470478 @default.
- W2975186974 hasConceptScore W2975186974C199539241 @default.
- W2975186974 hasConceptScore W2975186974C202444582 @default.
- W2975186974 hasConceptScore W2975186974C21547014 @default.
- W2975186974 hasConceptScore W2975186974C2776359362 @default.
- W2975186974 hasConceptScore W2975186974C2776502983 @default.
- W2975186974 hasConceptScore W2975186974C2777212361 @default.
- W2975186974 hasConceptScore W2975186974C2780012671 @default.