Matches in SemOpenAlex for { <https://semopenalex.org/work/W2558580397> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2558580397 endingPage "133" @default.
- W2558580397 startingPage "119" @default.
- W2558580397 abstract "The community has been going deeper and deeper in designing one cutting edge network after another, yet some works are there suggesting that we may have gone too far in this dimension. Some researchers unravelled a residual network into an exponentially wider one, and assorted the success of residual networks to fusing a large amount of relatively shallow models. Since some of their early claims are still not settled, we in this paper dig more on this topic, i.e., the unravelled view of residual networks. Based on that, we try to find a good compromise between the depth and width. Afterwards, we walk through a typical pipeline of developing a deep-learning-based algorithm. We start from a group of relatively shallow networks, which perform as well or even better than the current (much deeper) state-of-the-art models on the ImageNet classification dataset. Then, we initialize fully convolutional networks (FCNs) using our pre-trained models, and tune them for semantic image segmentation. Results show that the proposed networks, as pre-trained features, can boost existing methods a lot. Even without exhausting the sophistical techniques to improve the classic FCN model, we achieve comparable results with the best performers on four widely-used datasets, i.e., Cityscapes, PASCAL VOC, ADE20k and PASCAL-Context. The code and pre-trained models are released for public access1." @default.
- W2558580397 created "2016-12-08" @default.
- W2558580397 creator A5006294869 @default.
- W2558580397 creator A5020801818 @default.
- W2558580397 creator A5028024287 @default.
- W2558580397 date "2019-06-01" @default.
- W2558580397 modified "2023-10-17" @default.
- W2558580397 title "Wider or Deeper: Revisiting the ResNet Model for Visual Recognition" @default.
- W2558580397 cites W2037227137 @default.
- W2558580397 cites W2117539524 @default.
- W2558580397 cites W2296478878 @default.
- W2558580397 cites W2395611524 @default.
- W2558580397 cites W2412782625 @default.
- W2558580397 cites W2418033038 @default.
- W2558580397 cites W2560354825 @default.
- W2558580397 cites W2732026016 @default.
- W2558580397 cites W2789275762 @default.
- W2558580397 cites W2792765514 @default.
- W2558580397 cites W639708223 @default.
- W2558580397 doi "https://doi.org/10.1016/j.patcog.2019.01.006" @default.
- W2558580397 hasPublicationYear "2019" @default.
- W2558580397 type Work @default.
- W2558580397 sameAs 2558580397 @default.
- W2558580397 citedByCount "824" @default.
- W2558580397 countsByYear W25585803972016 @default.
- W2558580397 countsByYear W25585803972017 @default.
- W2558580397 countsByYear W25585803972018 @default.
- W2558580397 countsByYear W25585803972019 @default.
- W2558580397 countsByYear W25585803972020 @default.
- W2558580397 countsByYear W25585803972021 @default.
- W2558580397 countsByYear W25585803972022 @default.
- W2558580397 countsByYear W25585803972023 @default.
- W2558580397 crossrefType "journal-article" @default.
- W2558580397 hasAuthorship W2558580397A5006294869 @default.
- W2558580397 hasAuthorship W2558580397A5020801818 @default.
- W2558580397 hasAuthorship W2558580397A5028024287 @default.
- W2558580397 hasBestOaLocation W25585803972 @default.
- W2558580397 hasConcept C108583219 @default.
- W2558580397 hasConcept C11413529 @default.
- W2558580397 hasConcept C119857082 @default.
- W2558580397 hasConcept C151730666 @default.
- W2558580397 hasConcept C153180895 @default.
- W2558580397 hasConcept C154945302 @default.
- W2558580397 hasConcept C155512373 @default.
- W2558580397 hasConcept C162307627 @default.
- W2558580397 hasConcept C177264268 @default.
- W2558580397 hasConcept C199360897 @default.
- W2558580397 hasConcept C2776760102 @default.
- W2558580397 hasConcept C2779343474 @default.
- W2558580397 hasConcept C2944601119 @default.
- W2558580397 hasConcept C41008148 @default.
- W2558580397 hasConcept C43521106 @default.
- W2558580397 hasConcept C75608658 @default.
- W2558580397 hasConcept C86803240 @default.
- W2558580397 hasConcept C89600930 @default.
- W2558580397 hasConceptScore W2558580397C108583219 @default.
- W2558580397 hasConceptScore W2558580397C11413529 @default.
- W2558580397 hasConceptScore W2558580397C119857082 @default.
- W2558580397 hasConceptScore W2558580397C151730666 @default.
- W2558580397 hasConceptScore W2558580397C153180895 @default.
- W2558580397 hasConceptScore W2558580397C154945302 @default.
- W2558580397 hasConceptScore W2558580397C155512373 @default.
- W2558580397 hasConceptScore W2558580397C162307627 @default.
- W2558580397 hasConceptScore W2558580397C177264268 @default.
- W2558580397 hasConceptScore W2558580397C199360897 @default.
- W2558580397 hasConceptScore W2558580397C2776760102 @default.
- W2558580397 hasConceptScore W2558580397C2779343474 @default.
- W2558580397 hasConceptScore W2558580397C2944601119 @default.
- W2558580397 hasConceptScore W2558580397C41008148 @default.
- W2558580397 hasConceptScore W2558580397C43521106 @default.
- W2558580397 hasConceptScore W2558580397C75608658 @default.
- W2558580397 hasConceptScore W2558580397C86803240 @default.
- W2558580397 hasConceptScore W2558580397C89600930 @default.
- W2558580397 hasLocation W25585803971 @default.
- W2558580397 hasLocation W25585803972 @default.
- W2558580397 hasOpenAccess W2558580397 @default.
- W2558580397 hasPrimaryLocation W25585803971 @default.
- W2558580397 hasRelatedWork W2274287116 @default.
- W2558580397 hasRelatedWork W2964350391 @default.
- W2558580397 hasRelatedWork W2967403871 @default.
- W2558580397 hasRelatedWork W2983358626 @default.
- W2558580397 hasRelatedWork W2984708981 @default.
- W2558580397 hasRelatedWork W3087144180 @default.
- W2558580397 hasRelatedWork W3160076723 @default.
- W2558580397 hasRelatedWork W3196952692 @default.
- W2558580397 hasRelatedWork W3209312100 @default.
- W2558580397 hasRelatedWork W4300939921 @default.
- W2558580397 hasVolume "90" @default.
- W2558580397 isParatext "false" @default.
- W2558580397 isRetracted "false" @default.
- W2558580397 magId "2558580397" @default.
- W2558580397 workType "article" @default.