Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383109345> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4383109345 abstract "This work presents a new method for unsupervised thermal image classification and semantic segmentation by transferring knowledge from the RGB domain using a multi-domain attention network. Our method does not require any thermal annotations or co-registered RGB-thermal pairs, enabling robots to perform visual tasks at night and in adverse weather conditions without incurring additional costs of data labeling and registration. Current unsupervised domain adaptation methods look to align global images or features across domains. However, when the domain shift is significantly larger for cross-modal data, not all features can be transferred. We solve this problem by using a shared backbone network that promotes generalization, and domain-specific attention that reduces negative transfer by attending to domain-invariant and easily-transferable features. Our approach outperforms the state-of-the-art RGB-to-thermal adaptation method in classification benchmarks, and is successfully applied to thermal river scene segmentation using only synthetic RGB images. Our code is made publicly available at https://github.com/ganlumomo/thermal-uda-attention." @default.
- W4383109345 created "2023-07-05" @default.
- W4383109345 creator A5012208123 @default.
- W4383109345 creator A5031408324 @default.
- W4383109345 creator A5062371167 @default.
- W4383109345 date "2023-05-29" @default.
- W4383109345 modified "2023-10-16" @default.
- W4383109345 title "Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention Network" @default.
- W4383109345 cites W2105835272 @default.
- W4383109345 cites W2108598243 @default.
- W4383109345 cites W2214409633 @default.
- W4383109345 cites W2412782625 @default.
- W4383109345 cites W2473930607 @default.
- W4383109345 cites W2593768305 @default.
- W4383109345 cites W2752782242 @default.
- W4383109345 cites W2774839435 @default.
- W4383109345 cites W2904706552 @default.
- W4383109345 cites W2962687275 @default.
- W4383109345 cites W2962858109 @default.
- W4383109345 cites W2962864421 @default.
- W4383109345 cites W2962945654 @default.
- W4383109345 cites W2963107255 @default.
- W4383109345 cites W2981630749 @default.
- W4383109345 cites W3036463503 @default.
- W4383109345 cites W3039883906 @default.
- W4383109345 cites W3089035009 @default.
- W4383109345 cites W3118570274 @default.
- W4383109345 cites W3131439390 @default.
- W4383109345 cites W3180361602 @default.
- W4383109345 cites W3182674219 @default.
- W4383109345 cites W3202229469 @default.
- W4383109345 cites W3217181497 @default.
- W4383109345 cites W4200635035 @default.
- W4383109345 cites W4290995033 @default.
- W4383109345 cites W4292828877 @default.
- W4383109345 cites W4312527924 @default.
- W4383109345 cites W4312594135 @default.
- W4383109345 cites W639708223 @default.
- W4383109345 doi "https://doi.org/10.1109/icra48891.2023.10160872" @default.
- W4383109345 hasPublicationYear "2023" @default.
- W4383109345 type Work @default.
- W4383109345 citedByCount "0" @default.
- W4383109345 crossrefType "proceedings-article" @default.
- W4383109345 hasAuthorship W4383109345A5012208123 @default.
- W4383109345 hasAuthorship W4383109345A5031408324 @default.
- W4383109345 hasAuthorship W4383109345A5062371167 @default.
- W4383109345 hasBestOaLocation W43831093452 @default.
- W4383109345 hasConcept C119857082 @default.
- W4383109345 hasConcept C134306372 @default.
- W4383109345 hasConcept C153180895 @default.
- W4383109345 hasConcept C154945302 @default.
- W4383109345 hasConcept C177148314 @default.
- W4383109345 hasConcept C2776434776 @default.
- W4383109345 hasConcept C31972630 @default.
- W4383109345 hasConcept C33923547 @default.
- W4383109345 hasConcept C36503486 @default.
- W4383109345 hasConcept C41008148 @default.
- W4383109345 hasConcept C82990744 @default.
- W4383109345 hasConcept C89600930 @default.
- W4383109345 hasConcept C95623464 @default.
- W4383109345 hasConceptScore W4383109345C119857082 @default.
- W4383109345 hasConceptScore W4383109345C134306372 @default.
- W4383109345 hasConceptScore W4383109345C153180895 @default.
- W4383109345 hasConceptScore W4383109345C154945302 @default.
- W4383109345 hasConceptScore W4383109345C177148314 @default.
- W4383109345 hasConceptScore W4383109345C2776434776 @default.
- W4383109345 hasConceptScore W4383109345C31972630 @default.
- W4383109345 hasConceptScore W4383109345C33923547 @default.
- W4383109345 hasConceptScore W4383109345C36503486 @default.
- W4383109345 hasConceptScore W4383109345C41008148 @default.
- W4383109345 hasConceptScore W4383109345C82990744 @default.
- W4383109345 hasConceptScore W4383109345C89600930 @default.
- W4383109345 hasConceptScore W4383109345C95623464 @default.
- W4383109345 hasFunder F4320307103 @default.
- W4383109345 hasLocation W43831093451 @default.
- W4383109345 hasLocation W43831093452 @default.
- W4383109345 hasOpenAccess W4383109345 @default.
- W4383109345 hasPrimaryLocation W43831093451 @default.
- W4383109345 hasRelatedWork W2005437358 @default.
- W4383109345 hasRelatedWork W2134924024 @default.
- W4383109345 hasRelatedWork W2283162247 @default.
- W4383109345 hasRelatedWork W2517104666 @default.
- W4383109345 hasRelatedWork W2558375057 @default.
- W4383109345 hasRelatedWork W2739874619 @default.
- W4383109345 hasRelatedWork W2991444110 @default.
- W4383109345 hasRelatedWork W3147816421 @default.
- W4383109345 hasRelatedWork W4212983513 @default.
- W4383109345 hasRelatedWork W4288021053 @default.
- W4383109345 isParatext "false" @default.
- W4383109345 isRetracted "false" @default.
- W4383109345 workType "article" @default.