Matches in SemOpenAlex for { <https://semopenalex.org/work/W2981507930> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2981507930 endingPage "4664" @default.
- W2981507930 startingPage "4664" @default.
- W2981507930 abstract "The main objective of this work is to study the applicability of ensemble methods in the context of deep learning with limited amounts of labeled data. We exploit an ensemble of neural networks derived using Monte Carlo dropout, along with an ensemble of SVM classifiers which owes its effectiveness to the hand-crafted features used as inputs and to an active learning procedure. In order to leverage each classifier’s respective strengths, we combine them in an evidential framework, which models specifically their imprecision and uncertainty. The application we consider in order to illustrate the interest of our Multiple Classifier System is pedestrian detection in high-density crowds, which is ideally suited for its difficulty, cost of labeling and intrinsic imprecision of annotation data. We show that the fusion resulting from the effective modeling of uncertainty allows for performance improvement, and at the same time, for a deeper interpretation of the result in terms of commitment of the decision." @default.
- W2981507930 created "2019-11-01" @default.
- W2981507930 creator A5046687127 @default.
- W2981507930 creator A5055435924 @default.
- W2981507930 creator A5074824334 @default.
- W2981507930 date "2019-10-27" @default.
- W2981507930 modified "2023-09-27" @default.
- W2981507930 title "Augmenting Deep Learning Performance in an Evidential Multiple Classifier System" @default.
- W2981507930 cites W1996202725 @default.
- W2981507930 cites W2031454541 @default.
- W2981507930 cites W2039051707 @default.
- W2981507930 cites W2048196003 @default.
- W2981507930 cites W2057850321 @default.
- W2981507930 cites W2066843515 @default.
- W2981507930 cites W2072348410 @default.
- W2981507930 cites W2104853049 @default.
- W2981507930 cites W2111051539 @default.
- W2981507930 cites W2168356304 @default.
- W2981507930 cites W2197872593 @default.
- W2981507930 cites W2487437301 @default.
- W2981507930 cites W2729018917 @default.
- W2981507930 cites W2743905801 @default.
- W2981507930 cites W2801833814 @default.
- W2981507930 cites W2897403846 @default.
- W2981507930 cites W2899770378 @default.
- W2981507930 cites W2955669162 @default.
- W2981507930 cites W2963076262 @default.
- W2981507930 cites W2963315052 @default.
- W2981507930 cites W2963881378 @default.
- W2981507930 cites W2970395056 @default.
- W2981507930 cites W3106141888 @default.
- W2981507930 doi "https://doi.org/10.3390/s19214664" @default.
- W2981507930 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6864766" @default.
- W2981507930 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31717870" @default.
- W2981507930 hasPublicationYear "2019" @default.
- W2981507930 type Work @default.
- W2981507930 sameAs 2981507930 @default.
- W2981507930 citedByCount "0" @default.
- W2981507930 crossrefType "journal-article" @default.
- W2981507930 hasAuthorship W2981507930A5046687127 @default.
- W2981507930 hasAuthorship W2981507930A5055435924 @default.
- W2981507930 hasAuthorship W2981507930A5074824334 @default.
- W2981507930 hasBestOaLocation W29815079301 @default.
- W2981507930 hasConcept C119857082 @default.
- W2981507930 hasConcept C153083717 @default.
- W2981507930 hasConcept C154945302 @default.
- W2981507930 hasConcept C165696696 @default.
- W2981507930 hasConcept C2777852691 @default.
- W2981507930 hasConcept C38652104 @default.
- W2981507930 hasConcept C41008148 @default.
- W2981507930 hasConcept C45942800 @default.
- W2981507930 hasConcept C50644808 @default.
- W2981507930 hasConcept C95623464 @default.
- W2981507930 hasConceptScore W2981507930C119857082 @default.
- W2981507930 hasConceptScore W2981507930C153083717 @default.
- W2981507930 hasConceptScore W2981507930C154945302 @default.
- W2981507930 hasConceptScore W2981507930C165696696 @default.
- W2981507930 hasConceptScore W2981507930C2777852691 @default.
- W2981507930 hasConceptScore W2981507930C38652104 @default.
- W2981507930 hasConceptScore W2981507930C41008148 @default.
- W2981507930 hasConceptScore W2981507930C45942800 @default.
- W2981507930 hasConceptScore W2981507930C50644808 @default.
- W2981507930 hasConceptScore W2981507930C95623464 @default.
- W2981507930 hasIssue "21" @default.
- W2981507930 hasLocation W29815079301 @default.
- W2981507930 hasLocation W29815079302 @default.
- W2981507930 hasLocation W29815079303 @default.
- W2981507930 hasLocation W29815079304 @default.
- W2981507930 hasLocation W29815079305 @default.
- W2981507930 hasLocation W29815079306 @default.
- W2981507930 hasLocation W29815079307 @default.
- W2981507930 hasLocation W29815079308 @default.
- W2981507930 hasLocation W29815079309 @default.
- W2981507930 hasOpenAccess W2981507930 @default.
- W2981507930 hasPrimaryLocation W29815079301 @default.
- W2981507930 hasRelatedWork W2044507188 @default.
- W2981507930 hasRelatedWork W2968151853 @default.
- W2981507930 hasRelatedWork W3202701980 @default.
- W2981507930 hasRelatedWork W4205754593 @default.
- W2981507930 hasRelatedWork W4281560664 @default.
- W2981507930 hasRelatedWork W4281757034 @default.
- W2981507930 hasRelatedWork W4285046548 @default.
- W2981507930 hasRelatedWork W4285741730 @default.
- W2981507930 hasRelatedWork W4311847748 @default.
- W2981507930 hasRelatedWork W4313488044 @default.
- W2981507930 hasVolume "19" @default.
- W2981507930 isParatext "false" @default.
- W2981507930 isRetracted "false" @default.
- W2981507930 magId "2981507930" @default.
- W2981507930 workType "article" @default.