Matches in SemOpenAlex for { <https://semopenalex.org/work/W4301184422> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4301184422 abstract "Because UNet works well in learning damaged picture restoration from large-scale data, these models are commonly utilized in image dehazing applications. Transformer, another type of network design, has recently proven to be effective in natural language and complex visual tasks. Transformer models improve convolutional neural network limitations, but they fall short of UNet in terms of texture and detail repair. In this paper, we present an effective and efficient hierarchical encoder-decoder network architecture based on TransUNet. Our network has two core designs to make it suitable for this task. The first essential component is a TransUNet-based multi-scale dense feature fusion network, where we merge global self-attention from Transformer and multi-scale context data from UNet. The second essential component is our investigation of the Context Information Compensation Module to add-on data from the encoder to the decoder. With the use of these two designs, our strategy keeps the benefits of the conventional UNet network while enhancing the network with the new transformer’s superior performance in terms of global self-attention. The results of our experiments show that both the quantitative and qualitative evaluations are better than the current methods." @default.
- W4301184422 created "2022-10-04" @default.
- W4301184422 creator A5010818419 @default.
- W4301184422 creator A5032987260 @default.
- W4301184422 creator A5039414614 @default.
- W4301184422 creator A5079875253 @default.
- W4301184422 date "2022-08-19" @default.
- W4301184422 modified "2023-10-16" @default.
- W4301184422 title "TransID: Image Dehazing Based on TransUNet" @default.
- W4301184422 cites W2126926806 @default.
- W4301184422 cites W2133665775 @default.
- W4301184422 cites W2256362396 @default.
- W4301184422 cites W2467473805 @default.
- W4301184422 cites W2519481857 @default.
- W4301184422 cites W2779176852 @default.
- W4301184422 cites W2798876216 @default.
- W4301184422 cites W2895176907 @default.
- W4301184422 cites W2939217524 @default.
- W4301184422 cites W2948606054 @default.
- W4301184422 cites W2962754725 @default.
- W4301184422 cites W2963152299 @default.
- W4301184422 cites W2963306157 @default.
- W4301184422 cites W2963928582 @default.
- W4301184422 cites W2964080601 @default.
- W4301184422 cites W2983446232 @default.
- W4301184422 cites W3133769291 @default.
- W4301184422 cites W3138516171 @default.
- W4301184422 doi "https://doi.org/10.1109/prai55851.2022.9904061" @default.
- W4301184422 hasPublicationYear "2022" @default.
- W4301184422 type Work @default.
- W4301184422 citedByCount "0" @default.
- W4301184422 crossrefType "proceedings-article" @default.
- W4301184422 hasAuthorship W4301184422A5010818419 @default.
- W4301184422 hasAuthorship W4301184422A5032987260 @default.
- W4301184422 hasAuthorship W4301184422A5039414614 @default.
- W4301184422 hasAuthorship W4301184422A5079875253 @default.
- W4301184422 hasConcept C111919701 @default.
- W4301184422 hasConcept C118505674 @default.
- W4301184422 hasConcept C121332964 @default.
- W4301184422 hasConcept C154945302 @default.
- W4301184422 hasConcept C165801399 @default.
- W4301184422 hasConcept C193415008 @default.
- W4301184422 hasConcept C197129107 @default.
- W4301184422 hasConcept C23123220 @default.
- W4301184422 hasConcept C31258907 @default.
- W4301184422 hasConcept C41008148 @default.
- W4301184422 hasConcept C62520636 @default.
- W4301184422 hasConcept C66322947 @default.
- W4301184422 hasConcept C81363708 @default.
- W4301184422 hasConceptScore W4301184422C111919701 @default.
- W4301184422 hasConceptScore W4301184422C118505674 @default.
- W4301184422 hasConceptScore W4301184422C121332964 @default.
- W4301184422 hasConceptScore W4301184422C154945302 @default.
- W4301184422 hasConceptScore W4301184422C165801399 @default.
- W4301184422 hasConceptScore W4301184422C193415008 @default.
- W4301184422 hasConceptScore W4301184422C197129107 @default.
- W4301184422 hasConceptScore W4301184422C23123220 @default.
- W4301184422 hasConceptScore W4301184422C31258907 @default.
- W4301184422 hasConceptScore W4301184422C41008148 @default.
- W4301184422 hasConceptScore W4301184422C62520636 @default.
- W4301184422 hasConceptScore W4301184422C66322947 @default.
- W4301184422 hasConceptScore W4301184422C81363708 @default.
- W4301184422 hasLocation W43011844221 @default.
- W4301184422 hasOpenAccess W4301184422 @default.
- W4301184422 hasPrimaryLocation W43011844221 @default.
- W4301184422 hasRelatedWork W2517027266 @default.
- W4301184422 hasRelatedWork W3006334803 @default.
- W4301184422 hasRelatedWork W3091976719 @default.
- W4301184422 hasRelatedWork W3118457286 @default.
- W4301184422 hasRelatedWork W3194373887 @default.
- W4301184422 hasRelatedWork W4226106267 @default.
- W4301184422 hasRelatedWork W4226195305 @default.
- W4301184422 hasRelatedWork W4312545247 @default.
- W4301184422 hasRelatedWork W4320016073 @default.
- W4301184422 hasRelatedWork W4221141623 @default.
- W4301184422 isParatext "false" @default.
- W4301184422 isRetracted "false" @default.
- W4301184422 workType "article" @default.