Matches in SemOpenAlex for { <https://semopenalex.org/work/W2003699243> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2003699243 abstract "In this paper we propose a semi-supervised multiple instance learning based boosting algorithm for domain adaptation, with face detection as an example. Very often a generic classifier learned using a large volume of training data needs to be tuned to work for a specific scenario. However when deployed, the test scenarios may differ marginally from the training ones. For e.g. a face detection system may be deployed in an airport as well as in an auditorium hallway. The classifier then needs to adapt to the new domain. Instead of retraining the classifier completely using examples from the new scenario, it is desirable to see how much the classifier can self-learn. Conventional self-learning algorithms consider putative positives on test data given by the base classifier, and select a subset of those based on more stringent thresholds. In this paper we propose an alternative self-learning approach which is based on the popular multiple instance learning approach which makes use of instead of single instances for training the classifier. We pool the putative positives on a given test image into a positive bag and the putative negatives into a negative bag. We augment this data to the initial training data and retrain the classifier using MILBoost. Specifically the advantage of our approach is that since it makes use of bags it is more robust to classification errors by the base classifier. We demonstrate the improvement in classification accuracy using our approach on Faces in the Wild database. We show that our approach outperforms self-learning and compares favorably with MILBoost trained on manually marked face data without the corresponding increase in labeling effort." @default.
- W2003699243 created "2016-06-24" @default.
- W2003699243 creator A5002833804 @default.
- W2003699243 creator A5049669466 @default.
- W2003699243 creator A5054396431 @default.
- W2003699243 date "2012-12-16" @default.
- W2003699243 modified "2023-10-14" @default.
- W2003699243 title "Semi-supervised multiple instance learning based domain adaptation for object detection" @default.
- W2003699243 cites W2032558548 @default.
- W2003699243 cites W2033421762 @default.
- W2003699243 cites W2058685270 @default.
- W2003699243 cites W2079057609 @default.
- W2003699243 cites W2098693229 @default.
- W2003699243 cites W2109579504 @default.
- W2003699243 cites W2158379527 @default.
- W2003699243 cites W3097096317 @default.
- W2003699243 doi "https://doi.org/10.1145/2425333.2425346" @default.
- W2003699243 hasPublicationYear "2012" @default.
- W2003699243 type Work @default.
- W2003699243 sameAs 2003699243 @default.
- W2003699243 citedByCount "1" @default.
- W2003699243 countsByYear W20036992432022 @default.
- W2003699243 crossrefType "proceedings-article" @default.
- W2003699243 hasAuthorship W2003699243A5002833804 @default.
- W2003699243 hasAuthorship W2003699243A5049669466 @default.
- W2003699243 hasAuthorship W2003699243A5054396431 @default.
- W2003699243 hasConcept C119857082 @default.
- W2003699243 hasConcept C134306372 @default.
- W2003699243 hasConcept C139807058 @default.
- W2003699243 hasConcept C153180895 @default.
- W2003699243 hasConcept C154945302 @default.
- W2003699243 hasConcept C15744967 @default.
- W2003699243 hasConcept C169760540 @default.
- W2003699243 hasConcept C2776151529 @default.
- W2003699243 hasConcept C2776434776 @default.
- W2003699243 hasConcept C2781238097 @default.
- W2003699243 hasConcept C31972630 @default.
- W2003699243 hasConcept C33923547 @default.
- W2003699243 hasConcept C36503486 @default.
- W2003699243 hasConcept C41008148 @default.
- W2003699243 hasConcept C95623464 @default.
- W2003699243 hasConceptScore W2003699243C119857082 @default.
- W2003699243 hasConceptScore W2003699243C134306372 @default.
- W2003699243 hasConceptScore W2003699243C139807058 @default.
- W2003699243 hasConceptScore W2003699243C153180895 @default.
- W2003699243 hasConceptScore W2003699243C154945302 @default.
- W2003699243 hasConceptScore W2003699243C15744967 @default.
- W2003699243 hasConceptScore W2003699243C169760540 @default.
- W2003699243 hasConceptScore W2003699243C2776151529 @default.
- W2003699243 hasConceptScore W2003699243C2776434776 @default.
- W2003699243 hasConceptScore W2003699243C2781238097 @default.
- W2003699243 hasConceptScore W2003699243C31972630 @default.
- W2003699243 hasConceptScore W2003699243C33923547 @default.
- W2003699243 hasConceptScore W2003699243C36503486 @default.
- W2003699243 hasConceptScore W2003699243C41008148 @default.
- W2003699243 hasConceptScore W2003699243C95623464 @default.
- W2003699243 hasLocation W20036992431 @default.
- W2003699243 hasOpenAccess W2003699243 @default.
- W2003699243 hasPrimaryLocation W20036992431 @default.
- W2003699243 hasRelatedWork W1971759388 @default.
- W2003699243 hasRelatedWork W2004370856 @default.
- W2003699243 hasRelatedWork W2007544051 @default.
- W2003699243 hasRelatedWork W2021186063 @default.
- W2003699243 hasRelatedWork W2025800131 @default.
- W2003699243 hasRelatedWork W2035456249 @default.
- W2003699243 hasRelatedWork W2095705906 @default.
- W2003699243 hasRelatedWork W2129974284 @default.
- W2003699243 hasRelatedWork W2223320490 @default.
- W2003699243 hasRelatedWork W2975200075 @default.
- W2003699243 isParatext "false" @default.
- W2003699243 isRetracted "false" @default.
- W2003699243 magId "2003699243" @default.
- W2003699243 workType "article" @default.