Matches in SemOpenAlex for { <https://semopenalex.org/work/W2754136634> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2754136634 abstract "The rapid progress in visual recognition capabilities over the past several years can be attributed largely to improvements in generic and transferrable feature representations, particularly learned representations based on convolutional networks (convnets) trained “end-to-end” to predict visual semantics given raw pixel intensity values. In this thesis, we analyze the structure of these convnet representations and their generality and transferrability to other tasks and settings.We begin in Chapter 2 by examining the hierarchical semantic structure that naturally emerges in convnet representations from large-scale supervised training, even when this structure is unobserved in the training set. Empirically, the resulting representations generalize surprisingly well to classification in related yet distinct settings.Chapters 3 and 4 showcase the flexibility of convnet-based representations for prediction tasks where the inputs or targets have more complex structure. Chapter 3 focuses on representation transfer to the object detection and semantic segmentation tasks in which objects must be localized within an image, as well as labeled. Chapter 4 augments convnets with recurrent structure to handle recognition problems with sequential inputs (e.g., video activity recognition) or outputs (e.g., image captioning). Across each of these domains, end-to-end fine-tuning of the representation for the target task provides a substantial additional performance benefit.Finally, we address the necessity of label supervision for representation learning. In Chapter 5 we propose an unsupervised learning approach based on generative models, demonstrating that some of the transferrable semantic structure learned by supervised convnets can be learned from images alone." @default.
- W2754136634 created "2017-09-25" @default.
- W2754136634 creator A5012948584 @default.
- W2754136634 date "2017-01-01" @default.
- W2754136634 modified "2023-09-27" @default.
- W2754136634 title "Transferrable Representations for Visual Recognition" @default.
- W2754136634 hasPublicationYear "2017" @default.
- W2754136634 type Work @default.
- W2754136634 sameAs 2754136634 @default.
- W2754136634 citedByCount "0" @default.
- W2754136634 crossrefType "journal-article" @default.
- W2754136634 hasAuthorship W2754136634A5012948584 @default.
- W2754136634 hasConcept C105795698 @default.
- W2754136634 hasConcept C115961682 @default.
- W2754136634 hasConcept C119857082 @default.
- W2754136634 hasConcept C138885662 @default.
- W2754136634 hasConcept C153180895 @default.
- W2754136634 hasConcept C154945302 @default.
- W2754136634 hasConcept C15744967 @default.
- W2754136634 hasConcept C157657479 @default.
- W2754136634 hasConcept C162324750 @default.
- W2754136634 hasConcept C177264268 @default.
- W2754136634 hasConcept C17744445 @default.
- W2754136634 hasConcept C184337299 @default.
- W2754136634 hasConcept C187736073 @default.
- W2754136634 hasConcept C199360897 @default.
- W2754136634 hasConcept C199539241 @default.
- W2754136634 hasConcept C204321447 @default.
- W2754136634 hasConcept C2776359362 @default.
- W2754136634 hasConcept C2776401178 @default.
- W2754136634 hasConcept C2780451532 @default.
- W2754136634 hasConcept C2780598303 @default.
- W2754136634 hasConcept C2780767217 @default.
- W2754136634 hasConcept C2781238097 @default.
- W2754136634 hasConcept C33923547 @default.
- W2754136634 hasConcept C41008148 @default.
- W2754136634 hasConcept C41895202 @default.
- W2754136634 hasConcept C542102704 @default.
- W2754136634 hasConcept C59404180 @default.
- W2754136634 hasConcept C64876066 @default.
- W2754136634 hasConcept C81363708 @default.
- W2754136634 hasConcept C94625758 @default.
- W2754136634 hasConceptScore W2754136634C105795698 @default.
- W2754136634 hasConceptScore W2754136634C115961682 @default.
- W2754136634 hasConceptScore W2754136634C119857082 @default.
- W2754136634 hasConceptScore W2754136634C138885662 @default.
- W2754136634 hasConceptScore W2754136634C153180895 @default.
- W2754136634 hasConceptScore W2754136634C154945302 @default.
- W2754136634 hasConceptScore W2754136634C15744967 @default.
- W2754136634 hasConceptScore W2754136634C157657479 @default.
- W2754136634 hasConceptScore W2754136634C162324750 @default.
- W2754136634 hasConceptScore W2754136634C177264268 @default.
- W2754136634 hasConceptScore W2754136634C17744445 @default.
- W2754136634 hasConceptScore W2754136634C184337299 @default.
- W2754136634 hasConceptScore W2754136634C187736073 @default.
- W2754136634 hasConceptScore W2754136634C199360897 @default.
- W2754136634 hasConceptScore W2754136634C199539241 @default.
- W2754136634 hasConceptScore W2754136634C204321447 @default.
- W2754136634 hasConceptScore W2754136634C2776359362 @default.
- W2754136634 hasConceptScore W2754136634C2776401178 @default.
- W2754136634 hasConceptScore W2754136634C2780451532 @default.
- W2754136634 hasConceptScore W2754136634C2780598303 @default.
- W2754136634 hasConceptScore W2754136634C2780767217 @default.
- W2754136634 hasConceptScore W2754136634C2781238097 @default.
- W2754136634 hasConceptScore W2754136634C33923547 @default.
- W2754136634 hasConceptScore W2754136634C41008148 @default.
- W2754136634 hasConceptScore W2754136634C41895202 @default.
- W2754136634 hasConceptScore W2754136634C542102704 @default.
- W2754136634 hasConceptScore W2754136634C59404180 @default.
- W2754136634 hasConceptScore W2754136634C64876066 @default.
- W2754136634 hasConceptScore W2754136634C81363708 @default.
- W2754136634 hasConceptScore W2754136634C94625758 @default.
- W2754136634 hasLocation W27541366341 @default.
- W2754136634 hasOpenAccess W2754136634 @default.
- W2754136634 hasPrimaryLocation W27541366341 @default.
- W2754136634 hasRelatedWork W2155541015 @default.
- W2754136634 hasRelatedWork W2511012736 @default.
- W2754136634 hasRelatedWork W2521556056 @default.
- W2754136634 hasRelatedWork W2605480273 @default.
- W2754136634 hasRelatedWork W2623735101 @default.
- W2754136634 hasRelatedWork W2730987516 @default.
- W2754136634 hasRelatedWork W2743157634 @default.
- W2754136634 hasRelatedWork W2798271879 @default.
- W2754136634 hasRelatedWork W2804058931 @default.
- W2754136634 hasRelatedWork W2893615158 @default.
- W2754136634 hasRelatedWork W2946880267 @default.
- W2754136634 hasRelatedWork W2963081790 @default.
- W2754136634 hasRelatedWork W2963987879 @default.
- W2754136634 hasRelatedWork W2964293202 @default.
- W2754136634 hasRelatedWork W2998453661 @default.
- W2754136634 hasRelatedWork W3008503415 @default.
- W2754136634 hasRelatedWork W3022394231 @default.
- W2754136634 hasRelatedWork W3049323324 @default.
- W2754136634 hasRelatedWork W3105422445 @default.
- W2754136634 hasRelatedWork W3115964123 @default.
- W2754136634 isParatext "false" @default.
- W2754136634 isRetracted "false" @default.
- W2754136634 magId "2754136634" @default.
- W2754136634 workType "article" @default.