Matches in SemOpenAlex for { <https://semopenalex.org/work/W2015227583> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2015227583 abstract "Nowadays, classifiers play a core role in many computer vision tasks. The underlying assumption for learning classifiers is that the training set and the deployment environment (testing) follow the same probability distribution regarding the features used by the classifiers. However, in practice, there are different reasons that can break this constancy assumption. Accordingly, reusing existing classifiers by adapting them from the previous training environment (source domain) to the new testing one (target domain) is an approach with increasing acceptance in the computer vision community. In this paper we focus on the domain adaptation of deformable part-based models (DPMs) for object detection. In particular, we focus on a relatively unexplored scenario, i.e. incremental domain adaptation for object detection assuming weak-labeling. Therefore, our algorithm is ready to improve existing source-oriented DPM-based detectors as soon as a little amount of labeled target-domain training data is available, and keeps improving as more of such data arrives in a continuous fashion. For achieving this, we follow a multiple instance learning (MIL) paradigm that operates in an incremental per-image basis. As proof of concept, we address the challenging scenario of adapting a DPM-based pedestrian detector trained with synthetic pedestrians to operate in real-world scenarios. The obtained results show that our incremental adaptive models obtain equally good accuracy results as the batch learned models, while being more flexible for handling continuously arriving target-domain data." @default.
- W2015227583 created "2016-06-24" @default.
- W2015227583 creator A5004903288 @default.
- W2015227583 creator A5038017658 @default.
- W2015227583 creator A5049984637 @default.
- W2015227583 creator A5087248790 @default.
- W2015227583 date "2014-01-01" @default.
- W2015227583 modified "2023-09-23" @default.
- W2015227583 title "Incremental Domain Adaptation of Deformable Part-based Models" @default.
- W2015227583 cites W1722318740 @default.
- W2015227583 cites W1822439997 @default.
- W2015227583 cites W1834646128 @default.
- W2015227583 cites W2005295545 @default.
- W2015227583 cites W2031454541 @default.
- W2015227583 cites W2031489346 @default.
- W2015227583 cites W2033547469 @default.
- W2015227583 cites W2041280778 @default.
- W2015227583 cites W2079624250 @default.
- W2015227583 cites W2086686352 @default.
- W2015227583 cites W2098699644 @default.
- W2015227583 cites W2101974252 @default.
- W2015227583 cites W2109579504 @default.
- W2015227583 cites W2121955477 @default.
- W2015227583 cites W2134052170 @default.
- W2015227583 cites W2137023887 @default.
- W2015227583 cites W2141129816 @default.
- W2015227583 cites W2160218441 @default.
- W2015227583 cites W2162433343 @default.
- W2015227583 cites W2167706101 @default.
- W2015227583 cites W2168356304 @default.
- W2015227583 cites W2292423453 @default.
- W2015227583 cites W43161092 @default.
- W2015227583 doi "https://doi.org/10.5244/c.28.120" @default.
- W2015227583 hasPublicationYear "2014" @default.
- W2015227583 type Work @default.
- W2015227583 sameAs 2015227583 @default.
- W2015227583 citedByCount "32" @default.
- W2015227583 countsByYear W20152275832014 @default.
- W2015227583 countsByYear W20152275832015 @default.
- W2015227583 countsByYear W20152275832016 @default.
- W2015227583 countsByYear W20152275832017 @default.
- W2015227583 countsByYear W20152275832018 @default.
- W2015227583 countsByYear W20152275832019 @default.
- W2015227583 countsByYear W20152275832020 @default.
- W2015227583 countsByYear W20152275832021 @default.
- W2015227583 countsByYear W20152275832022 @default.
- W2015227583 crossrefType "proceedings-article" @default.
- W2015227583 hasAuthorship W2015227583A5004903288 @default.
- W2015227583 hasAuthorship W2015227583A5038017658 @default.
- W2015227583 hasAuthorship W2015227583A5049984637 @default.
- W2015227583 hasAuthorship W2015227583A5087248790 @default.
- W2015227583 hasBestOaLocation W20152275831 @default.
- W2015227583 hasConcept C134306372 @default.
- W2015227583 hasConcept C139807058 @default.
- W2015227583 hasConcept C154945302 @default.
- W2015227583 hasConcept C15744967 @default.
- W2015227583 hasConcept C169760540 @default.
- W2015227583 hasConcept C2776434776 @default.
- W2015227583 hasConcept C33923547 @default.
- W2015227583 hasConcept C36503486 @default.
- W2015227583 hasConcept C41008148 @default.
- W2015227583 hasConcept C95623464 @default.
- W2015227583 hasConceptScore W2015227583C134306372 @default.
- W2015227583 hasConceptScore W2015227583C139807058 @default.
- W2015227583 hasConceptScore W2015227583C154945302 @default.
- W2015227583 hasConceptScore W2015227583C15744967 @default.
- W2015227583 hasConceptScore W2015227583C169760540 @default.
- W2015227583 hasConceptScore W2015227583C2776434776 @default.
- W2015227583 hasConceptScore W2015227583C33923547 @default.
- W2015227583 hasConceptScore W2015227583C36503486 @default.
- W2015227583 hasConceptScore W2015227583C41008148 @default.
- W2015227583 hasConceptScore W2015227583C95623464 @default.
- W2015227583 hasLocation W20152275831 @default.
- W2015227583 hasOpenAccess W2015227583 @default.
- W2015227583 hasPrimaryLocation W20152275831 @default.
- W2015227583 hasRelatedWork W1864954421 @default.
- W2015227583 hasRelatedWork W2152148513 @default.
- W2015227583 hasRelatedWork W2280198878 @default.
- W2015227583 hasRelatedWork W2783380393 @default.
- W2015227583 hasRelatedWork W2951876757 @default.
- W2015227583 hasRelatedWork W3012432583 @default.
- W2015227583 hasRelatedWork W3096565154 @default.
- W2015227583 hasRelatedWork W4281397339 @default.
- W2015227583 hasRelatedWork W4283450023 @default.
- W2015227583 hasRelatedWork W4312910505 @default.
- W2015227583 isParatext "false" @default.
- W2015227583 isRetracted "false" @default.
- W2015227583 magId "2015227583" @default.
- W2015227583 workType "article" @default.