Matches in SemOpenAlex for { <https://semopenalex.org/work/W2803661804> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2803661804 endingPage "102969" @default.
- W2803661804 startingPage "102969" @default.
- W2803661804 abstract "Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependence on a given classifier hinders their performance. To address this problem, we propose classifier-agnostic saliency map extraction, which finds all parts of the image that any classifier could use, not just one given in advance. We observe that the proposed approach extracts higher quality saliency maps than prior work while being conceptually simple and easy to implement. The method sets the new state of the art result for localization task on the ImageNet data, outperforming all existing weakly-supervised localization techniques, despite not using the ground truth labels at the inference time. The code reproducing the results is available at https://github.com/kondiz/casme . The final version of this manuscript is published in Computer Vision and Image Understanding and is available online at https://doi.org/10.1016/j.cviu.2020.102969 ." @default.
- W2803661804 created "2018-06-01" @default.
- W2803661804 creator A5010954824 @default.
- W2803661804 creator A5032140556 @default.
- W2803661804 creator A5091175785 @default.
- W2803661804 date "2020-07-01" @default.
- W2803661804 modified "2023-10-14" @default.
- W2803661804 title "Classifier-agnostic saliency map extraction" @default.
- W2803661804 cites W1787224781 @default.
- W2803661804 cites W2012875423 @default.
- W2803661804 cites W2103559027 @default.
- W2803661804 cites W2128272608 @default.
- W2803661804 cites W2144764737 @default.
- W2803661804 cites W2496066288 @default.
- W2803661804 cites W2809710758 @default.
- W2803661804 doi "https://doi.org/10.1016/j.cviu.2020.102969" @default.
- W2803661804 hasPublicationYear "2020" @default.
- W2803661804 type Work @default.
- W2803661804 sameAs 2803661804 @default.
- W2803661804 citedByCount "11" @default.
- W2803661804 countsByYear W28036618042019 @default.
- W2803661804 countsByYear W28036618042020 @default.
- W2803661804 countsByYear W28036618042021 @default.
- W2803661804 countsByYear W28036618042022 @default.
- W2803661804 crossrefType "journal-article" @default.
- W2803661804 hasAuthorship W2803661804A5010954824 @default.
- W2803661804 hasAuthorship W2803661804A5032140556 @default.
- W2803661804 hasAuthorship W2803661804A5091175785 @default.
- W2803661804 hasBestOaLocation W28036618041 @default.
- W2803661804 hasConcept C119857082 @default.
- W2803661804 hasConcept C146849305 @default.
- W2803661804 hasConcept C153180895 @default.
- W2803661804 hasConcept C154945302 @default.
- W2803661804 hasConcept C2776145971 @default.
- W2803661804 hasConcept C2776214188 @default.
- W2803661804 hasConcept C41008148 @default.
- W2803661804 hasConcept C95623464 @default.
- W2803661804 hasConceptScore W2803661804C119857082 @default.
- W2803661804 hasConceptScore W2803661804C146849305 @default.
- W2803661804 hasConceptScore W2803661804C153180895 @default.
- W2803661804 hasConceptScore W2803661804C154945302 @default.
- W2803661804 hasConceptScore W2803661804C2776145971 @default.
- W2803661804 hasConceptScore W2803661804C2776214188 @default.
- W2803661804 hasConceptScore W2803661804C41008148 @default.
- W2803661804 hasConceptScore W2803661804C95623464 @default.
- W2803661804 hasFunder F4320309480 @default.
- W2803661804 hasFunder F4320309949 @default.
- W2803661804 hasFunder F4320316083 @default.
- W2803661804 hasLocation W28036618041 @default.
- W2803661804 hasLocation W28036618042 @default.
- W2803661804 hasLocation W28036618043 @default.
- W2803661804 hasLocation W28036618044 @default.
- W2803661804 hasOpenAccess W2803661804 @default.
- W2803661804 hasPrimaryLocation W28036618041 @default.
- W2803661804 hasRelatedWork W2001652754 @default.
- W2803661804 hasRelatedWork W2379065761 @default.
- W2803661804 hasRelatedWork W2549006548 @default.
- W2803661804 hasRelatedWork W2807311372 @default.
- W2803661804 hasRelatedWork W2961085424 @default.
- W2803661804 hasRelatedWork W3043252291 @default.
- W2803661804 hasRelatedWork W4214932115 @default.
- W2803661804 hasRelatedWork W4308671172 @default.
- W2803661804 hasRelatedWork W98693656 @default.
- W2803661804 hasRelatedWork W3158004940 @default.
- W2803661804 hasVolume "196" @default.
- W2803661804 isParatext "false" @default.
- W2803661804 isRetracted "false" @default.
- W2803661804 magId "2803661804" @default.
- W2803661804 workType "article" @default.