Matches in SemOpenAlex for { <https://semopenalex.org/work/W2794833903> ?p ?o ?g. }
- W2794833903 abstract "Existing logo detection methods usually consider a small number of logo classes and limited images per class with a strong assumption of requiring tedious object bounding box annotations, therefore not scalable to real-world dynamic applications. In this work, we tackle these challenges by exploring the webly data learning principle without the need for exhaustive manual labelling. Specifically, we propose a novel incremental learning approach, called Scalable Logo Self-co-Learning (SL^2), capable of automatically self-discovering informative training images from noisy web data for progressively improving model capability in a cross-model co-learning manner. Moreover, we introduce a very large (2,190,757 images of 194 logo classes) logo dataset WebLogo-2M by an automatic web data collection and processing method. Extensive comparative evaluations demonstrate the superiority of the proposed SL^2 method over the state-of-the-art strongly and weakly supervised detection models and contemporary webly data learning approaches." @default.
- W2794833903 created "2018-04-06" @default.
- W2794833903 creator A5015663174 @default.
- W2794833903 creator A5028643592 @default.
- W2794833903 creator A5039302902 @default.
- W2794833903 date "2018-03-30" @default.
- W2794833903 modified "2023-10-17" @default.
- W2794833903 title "Scalable Deep Learning Logo Detection." @default.
- W2794833903 cites W1686810756 @default.
- W2794833903 cites W1756896031 @default.
- W2794833903 cites W1824737917 @default.
- W2794833903 cites W1861492603 @default.
- W2794833903 cites W1977805283 @default.
- W2794833903 cites W2003813371 @default.
- W2794833903 cites W2031039904 @default.
- W2794833903 cites W2037227137 @default.
- W2794833903 cites W2037603696 @default.
- W2794833903 cites W2040335539 @default.
- W2794833903 cites W2044557744 @default.
- W2794833903 cites W2085443648 @default.
- W2794833903 cites W2102605133 @default.
- W2794833903 cites W2103577800 @default.
- W2794833903 cites W2117539524 @default.
- W2794833903 cites W2118978333 @default.
- W2794833903 cites W2123024445 @default.
- W2794833903 cites W2133324800 @default.
- W2794833903 cites W2219856611 @default.
- W2794833903 cites W2325939864 @default.
- W2794833903 cites W2441255125 @default.
- W2794833903 cites W2560129302 @default.
- W2794833903 cites W2570343428 @default.
- W2794833903 cites W2614259740 @default.
- W2794833903 cites W2776722832 @default.
- W2794833903 cites W2792076282 @default.
- W2794833903 cites W2949667497 @default.
- W2794833903 cites W2950931866 @default.
- W2794833903 cites W2951084305 @default.
- W2794833903 cites W2951548327 @default.
- W2794833903 cites W2953106684 @default.
- W2794833903 cites W2953391683 @default.
- W2794833903 cites W2963331658 @default.
- W2794833903 cites W3106250896 @default.
- W2794833903 cites W7746136 @default.
- W2794833903 cites W967544008 @default.
- W2794833903 hasPublicationYear "2018" @default.
- W2794833903 type Work @default.
- W2794833903 sameAs 2794833903 @default.
- W2794833903 citedByCount "4" @default.
- W2794833903 countsByYear W27948339032019 @default.
- W2794833903 countsByYear W27948339032020 @default.
- W2794833903 crossrefType "posted-content" @default.
- W2794833903 hasAuthorship W2794833903A5015663174 @default.
- W2794833903 hasAuthorship W2794833903A5028643592 @default.
- W2794833903 hasAuthorship W2794833903A5039302902 @default.
- W2794833903 hasConcept C108583219 @default.
- W2794833903 hasConcept C115961682 @default.
- W2794833903 hasConcept C119857082 @default.
- W2794833903 hasConcept C136389625 @default.
- W2794833903 hasConcept C147037132 @default.
- W2794833903 hasConcept C154945302 @default.
- W2794833903 hasConcept C199360897 @default.
- W2794833903 hasConcept C2777212361 @default.
- W2794833903 hasConcept C2778720087 @default.
- W2794833903 hasConcept C2781238097 @default.
- W2794833903 hasConcept C41008148 @default.
- W2794833903 hasConcept C48044578 @default.
- W2794833903 hasConcept C50644808 @default.
- W2794833903 hasConcept C63584917 @default.
- W2794833903 hasConcept C77088390 @default.
- W2794833903 hasConceptScore W2794833903C108583219 @default.
- W2794833903 hasConceptScore W2794833903C115961682 @default.
- W2794833903 hasConceptScore W2794833903C119857082 @default.
- W2794833903 hasConceptScore W2794833903C136389625 @default.
- W2794833903 hasConceptScore W2794833903C147037132 @default.
- W2794833903 hasConceptScore W2794833903C154945302 @default.
- W2794833903 hasConceptScore W2794833903C199360897 @default.
- W2794833903 hasConceptScore W2794833903C2777212361 @default.
- W2794833903 hasConceptScore W2794833903C2778720087 @default.
- W2794833903 hasConceptScore W2794833903C2781238097 @default.
- W2794833903 hasConceptScore W2794833903C41008148 @default.
- W2794833903 hasConceptScore W2794833903C48044578 @default.
- W2794833903 hasConceptScore W2794833903C50644808 @default.
- W2794833903 hasConceptScore W2794833903C63584917 @default.
- W2794833903 hasConceptScore W2794833903C77088390 @default.
- W2794833903 hasLocation W27948339031 @default.
- W2794833903 hasOpenAccess W2794833903 @default.
- W2794833903 hasPrimaryLocation W27948339031 @default.
- W2794833903 hasRelatedWork W130907108 @default.
- W2794833903 hasRelatedWork W1499276978 @default.
- W2794833903 hasRelatedWork W1739260168 @default.
- W2794833903 hasRelatedWork W1938425378 @default.
- W2794833903 hasRelatedWork W2026566343 @default.
- W2794833903 hasRelatedWork W2578908617 @default.
- W2794833903 hasRelatedWork W2625367499 @default.
- W2794833903 hasRelatedWork W2753179890 @default.
- W2794833903 hasRelatedWork W2769805767 @default.
- W2794833903 hasRelatedWork W2776277180 @default.
- W2794833903 hasRelatedWork W2796418006 @default.
- W2794833903 hasRelatedWork W2801347102 @default.
- W2794833903 hasRelatedWork W2803484693 @default.