Matches in SemOpenAlex for { <https://semopenalex.org/work/W2730741641> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2730741641 abstract "Crowding is a visual effect suffered by humans, in which an object that can be recognized in isolation can no longer be recognized when other objects, called flankers, are placed close to it. In this work, we study the effect of crowding in artificial Deep Neural Networks for object recognition. We analyze both standard deep convolutional neural networks (DCNNs) as well as a new version of DCNNs which is 1) multi-scale and 2) with size of the convolution filters change depending on the eccentricity wrt to the center of fixation. Such networks, that we call eccentricity-dependent, are a computational model of the feedforward path of the primate visual cortex. Our results reveal that the eccentricity-dependent model, trained on target objects in isolation, can recognize such targets in the presence of flankers, if the targets are near the center of the image, whereas DCNNs cannot. Also, for all tested networks, when trained on targets in isolation, we find that recognition accuracy of the networks decreases the closer the flankers are to the target and the more flankers there are. We find that visual similarity between the target and flankers also plays a role and that pooling in early layers of the network leads to more crowding. Additionally, we show that incorporating the flankers into the images of the training set does not improve performance with crowding." @default.
- W2730741641 created "2017-07-14" @default.
- W2730741641 creator A5001833084 @default.
- W2730741641 creator A5025034643 @default.
- W2730741641 creator A5037294561 @default.
- W2730741641 date "2017-06-26" @default.
- W2730741641 modified "2023-09-27" @default.
- W2730741641 title "Do Deep Neural Networks Suffer from Crowding" @default.
- W2730741641 cites W1686810756 @default.
- W2730741641 cites W2016484041 @default.
- W2730741641 cites W2019790087 @default.
- W2730741641 cites W2044147198 @default.
- W2730741641 cites W2064885356 @default.
- W2730741641 cites W2097117768 @default.
- W2730741641 cites W2112796928 @default.
- W2730741641 cites W2194321275 @default.
- W2730741641 cites W2194775991 @default.
- W2730741641 cites W2217248474 @default.
- W2730741641 cites W2289831813 @default.
- W2730741641 cites W2768532499 @default.
- W2730741641 cites W2963207607 @default.
- W2730741641 hasPublicationYear "2017" @default.
- W2730741641 type Work @default.
- W2730741641 sameAs 2730741641 @default.
- W2730741641 citedByCount "0" @default.
- W2730741641 crossrefType "posted-content" @default.
- W2730741641 hasAuthorship W2730741641A5001833084 @default.
- W2730741641 hasAuthorship W2730741641A5025034643 @default.
- W2730741641 hasAuthorship W2730741641A5037294561 @default.
- W2730741641 hasConcept C149333683 @default.
- W2730741641 hasConcept C153180895 @default.
- W2730741641 hasConcept C154945302 @default.
- W2730741641 hasConcept C15744967 @default.
- W2730741641 hasConcept C169760540 @default.
- W2730741641 hasConcept C2779345533 @default.
- W2730741641 hasConcept C31972630 @default.
- W2730741641 hasConcept C41008148 @default.
- W2730741641 hasConcept C52622490 @default.
- W2730741641 hasConcept C64876066 @default.
- W2730741641 hasConcept C81363708 @default.
- W2730741641 hasConceptScore W2730741641C149333683 @default.
- W2730741641 hasConceptScore W2730741641C153180895 @default.
- W2730741641 hasConceptScore W2730741641C154945302 @default.
- W2730741641 hasConceptScore W2730741641C15744967 @default.
- W2730741641 hasConceptScore W2730741641C169760540 @default.
- W2730741641 hasConceptScore W2730741641C2779345533 @default.
- W2730741641 hasConceptScore W2730741641C31972630 @default.
- W2730741641 hasConceptScore W2730741641C41008148 @default.
- W2730741641 hasConceptScore W2730741641C52622490 @default.
- W2730741641 hasConceptScore W2730741641C64876066 @default.
- W2730741641 hasConceptScore W2730741641C81363708 @default.
- W2730741641 hasLocation W27307416411 @default.
- W2730741641 hasOpenAccess W2730741641 @default.
- W2730741641 hasPrimaryLocation W27307416411 @default.
- W2730741641 hasRelatedWork W144325277 @default.
- W2730741641 hasRelatedWork W1969498556 @default.
- W2730741641 hasRelatedWork W2071245907 @default.
- W2730741641 hasRelatedWork W2076469056 @default.
- W2730741641 hasRelatedWork W2078963882 @default.
- W2730741641 hasRelatedWork W2105227524 @default.
- W2730741641 hasRelatedWork W2148036198 @default.
- W2730741641 hasRelatedWork W2387550627 @default.
- W2730741641 hasRelatedWork W2400545144 @default.
- W2730741641 hasRelatedWork W2608261048 @default.
- W2730741641 hasRelatedWork W2748436136 @default.
- W2730741641 hasRelatedWork W2782660124 @default.
- W2730741641 hasRelatedWork W2884547081 @default.
- W2730741641 hasRelatedWork W2900896837 @default.
- W2730741641 hasRelatedWork W2908322845 @default.
- W2730741641 hasRelatedWork W3025069833 @default.
- W2730741641 hasRelatedWork W3098596645 @default.
- W2730741641 hasRelatedWork W3112323501 @default.
- W2730741641 hasRelatedWork W3211206887 @default.
- W2730741641 hasRelatedWork W1976330818 @default.
- W2730741641 isParatext "false" @default.
- W2730741641 isRetracted "false" @default.
- W2730741641 magId "2730741641" @default.
- W2730741641 workType "article" @default.