Matches in SemOpenAlex for { <https://semopenalex.org/work/W2917742022> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2917742022 abstract "Deep Convolutional Neural Networks (CNNs) have been repeatedly shown to perform well on image classification tasks, successfully recognizing a broad array of objects when given sufficient training data. Methods for object localization, however, are still in need of substantial improvement. In this paper, we offer a fundamentally different approach to the localization of recognized objects in images. Our method is predicated on the idea that a deep CNN capable of recognizing an object must implicitly contain knowledge about object location in its connection weights. We provide a simple method to interpret classifier weights in the context of individual classified images. This method involves the calculation of the derivative of network generated activation patterns, such as the activation of output class label units, with regard to each input pixel, performing a sensitivity analysis that identifies the pixels that, in a local sense, have the greatest influence on internal representations and object recognition. These derivatives can be efficiently computed using a single backward pass through the deep CNN classifier, producing a sensitivity map of the image. We demonstrate that a simple linear mapping can be learned from sensitivity maps to bounding box coordinates, localizing the recognized object. Our experimental results, using real-world data sets for which ground truth localization information is known, reveal competitive accuracy from our fast technique." @default.
- W2917742022 created "2019-03-02" @default.
- W2917742022 creator A5050674828 @default.
- W2917742022 creator A5050745506 @default.
- W2917742022 date "2019-01-01" @default.
- W2917742022 modified "2023-09-23" @default.
- W2917742022 title "Fast Object Localization via Sensitivity Analysis" @default.
- W2917742022 cites W1498436455 @default.
- W2917742022 cites W1536680647 @default.
- W2917742022 cites W1575299770 @default.
- W2917742022 cites W1919709169 @default.
- W2917742022 cites W1966601141 @default.
- W2917742022 cites W2016016818 @default.
- W2917742022 cites W2062118960 @default.
- W2917742022 cites W2079267072 @default.
- W2917742022 cites W2108598243 @default.
- W2917742022 cites W2295107390 @default.
- W2917742022 cites W2441255125 @default.
- W2917742022 cites W2913340405 @default.
- W2917742022 cites W2922086296 @default.
- W2917742022 cites W2963150697 @default.
- W2917742022 doi "https://doi.org/10.1007/978-3-030-33723-0_17" @default.
- W2917742022 hasPublicationYear "2019" @default.
- W2917742022 type Work @default.
- W2917742022 sameAs 2917742022 @default.
- W2917742022 citedByCount "3" @default.
- W2917742022 countsByYear W29177420222020 @default.
- W2917742022 crossrefType "book-chapter" @default.
- W2917742022 hasAuthorship W2917742022A5050674828 @default.
- W2917742022 hasAuthorship W2917742022A5050745506 @default.
- W2917742022 hasConcept C115961682 @default.
- W2917742022 hasConcept C127413603 @default.
- W2917742022 hasConcept C147037132 @default.
- W2917742022 hasConcept C153180895 @default.
- W2917742022 hasConcept C154945302 @default.
- W2917742022 hasConcept C160633673 @default.
- W2917742022 hasConcept C21200559 @default.
- W2917742022 hasConcept C24326235 @default.
- W2917742022 hasConcept C2776151529 @default.
- W2917742022 hasConcept C2781238097 @default.
- W2917742022 hasConcept C31972630 @default.
- W2917742022 hasConcept C41008148 @default.
- W2917742022 hasConcept C50644808 @default.
- W2917742022 hasConcept C63584917 @default.
- W2917742022 hasConcept C64876066 @default.
- W2917742022 hasConcept C81363708 @default.
- W2917742022 hasConcept C95623464 @default.
- W2917742022 hasConceptScore W2917742022C115961682 @default.
- W2917742022 hasConceptScore W2917742022C127413603 @default.
- W2917742022 hasConceptScore W2917742022C147037132 @default.
- W2917742022 hasConceptScore W2917742022C153180895 @default.
- W2917742022 hasConceptScore W2917742022C154945302 @default.
- W2917742022 hasConceptScore W2917742022C160633673 @default.
- W2917742022 hasConceptScore W2917742022C21200559 @default.
- W2917742022 hasConceptScore W2917742022C24326235 @default.
- W2917742022 hasConceptScore W2917742022C2776151529 @default.
- W2917742022 hasConceptScore W2917742022C2781238097 @default.
- W2917742022 hasConceptScore W2917742022C31972630 @default.
- W2917742022 hasConceptScore W2917742022C41008148 @default.
- W2917742022 hasConceptScore W2917742022C50644808 @default.
- W2917742022 hasConceptScore W2917742022C63584917 @default.
- W2917742022 hasConceptScore W2917742022C64876066 @default.
- W2917742022 hasConceptScore W2917742022C81363708 @default.
- W2917742022 hasConceptScore W2917742022C95623464 @default.
- W2917742022 hasLocation W29177420221 @default.
- W2917742022 hasOpenAccess W2917742022 @default.
- W2917742022 hasPrimaryLocation W29177420221 @default.
- W2917742022 hasRelatedWork W1994488211 @default.
- W2917742022 hasRelatedWork W2039305695 @default.
- W2917742022 hasRelatedWork W2095705906 @default.
- W2917742022 hasRelatedWork W2290280043 @default.
- W2917742022 hasRelatedWork W2553415931 @default.
- W2917742022 hasRelatedWork W2801801420 @default.
- W2917742022 hasRelatedWork W2889698616 @default.
- W2917742022 hasRelatedWork W2922421953 @default.
- W2917742022 hasRelatedWork W3090948685 @default.
- W2917742022 hasRelatedWork W3122675077 @default.
- W2917742022 isParatext "false" @default.
- W2917742022 isRetracted "false" @default.
- W2917742022 magId "2917742022" @default.
- W2917742022 workType "book-chapter" @default.