Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288022134> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W4288022134 abstract "Compositional convolutional networks are generative compositional models of neural network features, that achieve state of the art results when classifying partially occluded objects, even when they have not been exposed to occluded objects during training. In this work, we study the performance of CompositionalNets at localizing occluders in images. We show that the original model is not able to localize occluders well. We propose to overcome this limitation by modeling the feature activations as a mixture of von-Mises-Fisher distributions, which also allows for an end-to-end training of CompositionalNets. Our experimental results demonstrate that the proposed extensions increase the model's performance at localizing occluders as well as at classifying partially occluded objects." @default.
- W4288022134 created "2022-07-26" @default.
- W4288022134 creator A5004325726 @default.
- W4288022134 creator A5017941291 @default.
- W4288022134 creator A5034551921 @default.
- W4288022134 creator A5084928022 @default.
- W4288022134 creator A5086706224 @default.
- W4288022134 date "2019-11-18" @default.
- W4288022134 modified "2023-10-16" @default.
- W4288022134 title "Localizing Occluders with Compositional Convolutional Networks" @default.
- W4288022134 doi "https://doi.org/10.48550/arxiv.1911.08571" @default.
- W4288022134 hasPublicationYear "2019" @default.
- W4288022134 type Work @default.
- W4288022134 citedByCount "0" @default.
- W4288022134 crossrefType "posted-content" @default.
- W4288022134 hasAuthorship W4288022134A5004325726 @default.
- W4288022134 hasAuthorship W4288022134A5017941291 @default.
- W4288022134 hasAuthorship W4288022134A5034551921 @default.
- W4288022134 hasAuthorship W4288022134A5084928022 @default.
- W4288022134 hasAuthorship W4288022134A5086706224 @default.
- W4288022134 hasBestOaLocation W42880221341 @default.
- W4288022134 hasConcept C138885662 @default.
- W4288022134 hasConcept C153180895 @default.
- W4288022134 hasConcept C154945302 @default.
- W4288022134 hasConcept C2776401178 @default.
- W4288022134 hasConcept C31972630 @default.
- W4288022134 hasConcept C39890363 @default.
- W4288022134 hasConcept C41008148 @default.
- W4288022134 hasConcept C41895202 @default.
- W4288022134 hasConcept C81363708 @default.
- W4288022134 hasConceptScore W4288022134C138885662 @default.
- W4288022134 hasConceptScore W4288022134C153180895 @default.
- W4288022134 hasConceptScore W4288022134C154945302 @default.
- W4288022134 hasConceptScore W4288022134C2776401178 @default.
- W4288022134 hasConceptScore W4288022134C31972630 @default.
- W4288022134 hasConceptScore W4288022134C39890363 @default.
- W4288022134 hasConceptScore W4288022134C41008148 @default.
- W4288022134 hasConceptScore W4288022134C41895202 @default.
- W4288022134 hasConceptScore W4288022134C81363708 @default.
- W4288022134 hasLocation W42880221341 @default.
- W4288022134 hasLocation W42880221342 @default.
- W4288022134 hasOpenAccess W4288022134 @default.
- W4288022134 hasPrimaryLocation W42880221341 @default.
- W4288022134 hasRelatedWork W1504288058 @default.
- W4288022134 hasRelatedWork W2017205855 @default.
- W4288022134 hasRelatedWork W2048505601 @default.
- W4288022134 hasRelatedWork W2116675934 @default.
- W4288022134 hasRelatedWork W2167293474 @default.
- W4288022134 hasRelatedWork W2175746458 @default.
- W4288022134 hasRelatedWork W2331674254 @default.
- W4288022134 hasRelatedWork W2760085659 @default.
- W4288022134 hasRelatedWork W3042897387 @default.
- W4288022134 hasRelatedWork W3093612317 @default.
- W4288022134 isParatext "false" @default.
- W4288022134 isRetracted "false" @default.
- W4288022134 workType "article" @default.