Matches in SemOpenAlex for { <https://semopenalex.org/work/W1857221572> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W1857221572 endingPage "368" @default.
- W1857221572 startingPage "355" @default.
- W1857221572 abstract "The recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. However, these annotations may be imperfect, in the sense that many images contain multiple objects belonging to the label vocabulary. In other words, we have a multi-label problem but the annotations include only a single label (and not necessarily the most prominent). Such a setting motivates the use of a robust evaluation measure, which allows for a limited number of labels to be predicted and, as long as one of the predicted labels is correct, the overall prediction should be considered correct. This is indeed the type of evaluation measure used to assess algorithm performance in a recent competition on ImageNet data. Optimizing such types of performance measures presents several hurdles even with existing structured output learning methods. Indeed, many of the current state-of-the-art methods optimize the prediction of only a single output label, ignoring this ‘structure’ altogether. In this paper, we show how to directly optimize continuous surrogates of such performance measures using structured output learning techniques with latent variables. We use the output of existing binary classifiers as input features in a new learning stage which optimizes the structured loss corresponding to the robust performance measure. We present empirical evidence that this allows us to ‘boost’ the performance of existing binary classifiers which are the state-of-the-art for the task of object classification in ImageNet." @default.
- W1857221572 created "2016-06-24" @default.
- W1857221572 creator A5021827617 @default.
- W1857221572 creator A5030482411 @default.
- W1857221572 creator A5071163800 @default.
- W1857221572 date "2011-01-01" @default.
- W1857221572 modified "2023-09-23" @default.
- W1857221572 title "Optimization of Robust Loss Functions for Weakly-Labeled Image Taxonomies: An ImageNet Case Study" @default.
- W1857221572 cites W1606858007 @default.
- W1857221572 cites W1959000896 @default.
- W1857221572 cites W2005688170 @default.
- W1857221572 cites W2031489346 @default.
- W1857221572 cites W2108598243 @default.
- W1857221572 cites W2128154306 @default.
- W1857221572 cites W2145607950 @default.
- W1857221572 cites W2147196093 @default.
- W1857221572 doi "https://doi.org/10.1007/978-3-642-23094-3_26" @default.
- W1857221572 hasPublicationYear "2011" @default.
- W1857221572 type Work @default.
- W1857221572 sameAs 1857221572 @default.
- W1857221572 citedByCount "3" @default.
- W1857221572 countsByYear W18572215722018 @default.
- W1857221572 countsByYear W18572215722020 @default.
- W1857221572 crossrefType "book-chapter" @default.
- W1857221572 hasAuthorship W1857221572A5021827617 @default.
- W1857221572 hasAuthorship W1857221572A5030482411 @default.
- W1857221572 hasAuthorship W1857221572A5071163800 @default.
- W1857221572 hasBestOaLocation W18572215722 @default.
- W1857221572 hasConcept C115961682 @default.
- W1857221572 hasConcept C119857082 @default.
- W1857221572 hasConcept C124101348 @default.
- W1857221572 hasConcept C138885662 @default.
- W1857221572 hasConcept C153180895 @default.
- W1857221572 hasConcept C154945302 @default.
- W1857221572 hasConcept C162324750 @default.
- W1857221572 hasConcept C187736073 @default.
- W1857221572 hasConcept C22367795 @default.
- W1857221572 hasConcept C2777601683 @default.
- W1857221572 hasConcept C2780009758 @default.
- W1857221572 hasConcept C2780310539 @default.
- W1857221572 hasConcept C2780451532 @default.
- W1857221572 hasConcept C2781238097 @default.
- W1857221572 hasConcept C33923547 @default.
- W1857221572 hasConcept C41008148 @default.
- W1857221572 hasConcept C41895202 @default.
- W1857221572 hasConcept C48372109 @default.
- W1857221572 hasConcept C94375191 @default.
- W1857221572 hasConceptScore W1857221572C115961682 @default.
- W1857221572 hasConceptScore W1857221572C119857082 @default.
- W1857221572 hasConceptScore W1857221572C124101348 @default.
- W1857221572 hasConceptScore W1857221572C138885662 @default.
- W1857221572 hasConceptScore W1857221572C153180895 @default.
- W1857221572 hasConceptScore W1857221572C154945302 @default.
- W1857221572 hasConceptScore W1857221572C162324750 @default.
- W1857221572 hasConceptScore W1857221572C187736073 @default.
- W1857221572 hasConceptScore W1857221572C22367795 @default.
- W1857221572 hasConceptScore W1857221572C2777601683 @default.
- W1857221572 hasConceptScore W1857221572C2780009758 @default.
- W1857221572 hasConceptScore W1857221572C2780310539 @default.
- W1857221572 hasConceptScore W1857221572C2780451532 @default.
- W1857221572 hasConceptScore W1857221572C2781238097 @default.
- W1857221572 hasConceptScore W1857221572C33923547 @default.
- W1857221572 hasConceptScore W1857221572C41008148 @default.
- W1857221572 hasConceptScore W1857221572C41895202 @default.
- W1857221572 hasConceptScore W1857221572C48372109 @default.
- W1857221572 hasConceptScore W1857221572C94375191 @default.
- W1857221572 hasLocation W18572215721 @default.
- W1857221572 hasLocation W18572215722 @default.
- W1857221572 hasOpenAccess W1857221572 @default.
- W1857221572 hasPrimaryLocation W18572215721 @default.
- W1857221572 hasRelatedWork W1981726727 @default.
- W1857221572 hasRelatedWork W2092957489 @default.
- W1857221572 hasRelatedWork W2388832585 @default.
- W1857221572 hasRelatedWork W2536452361 @default.
- W1857221572 hasRelatedWork W2767828440 @default.
- W1857221572 hasRelatedWork W2961085424 @default.
- W1857221572 hasRelatedWork W4286629047 @default.
- W1857221572 hasRelatedWork W4306674287 @default.
- W1857221572 hasRelatedWork W2992698285 @default.
- W1857221572 hasRelatedWork W4224009465 @default.
- W1857221572 isParatext "false" @default.
- W1857221572 isRetracted "false" @default.
- W1857221572 magId "1857221572" @default.
- W1857221572 workType "book-chapter" @default.