FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3102532606> ?p ?o ?g. }

• W3102532606 abstract "Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In this paper, we present a domain-invariant representation learning (DIRL) algorithm to adapt deep models to the physical environment with a small amount of real data. Existing approaches that only mitigate the covariate shift by aligning the marginal distributions across the domains and assume the conditional distributions to be domain-invariant can lead to ambiguous transfer in real scenarios. We propose to jointly align the marginal (input domains) and the conditional (output labels) distributions to mitigate the covariate and the conditional shift across the domains with adversarial learning, and combine it with a triplet distribution loss to make the conditional distributions disjoint in the shared feature space. Experiments on digit domains yield state-of-the-art performance on challenging benchmarks, while sim-to-real transfer of object recognition for vision-based decluttering with a mobile robot improves from 26.8 % to 91.0 %, resulting in 86.5 % grasping accuracy of a wide variety of objects. Code and supplementary details are available at this https URL" @default.
• W3102532606 created "2020-11-23" @default.
• W3102532606 creator A5088063475 @default.
• W3102532606 date "2020-11-15" @default.
• W3102532606 modified "2023-09-27" @default.
• W3102532606 title "Domain-Invariant Representation Learning for Sim-to-Real Transfer" @default.
• W3102532606 cites W1722318740 @default.
• W3102532606 cites W1731081199 @default.
• W3102532606 cites W2041376653 @default.
• W3102532606 cites W2046752996 @default.
• W3102532606 cites W2096943734 @default.
• W3102532606 cites W2100659887 @default.
• W3102532606 cites W2104094955 @default.
• W3102532606 cites W2162651021 @default.
• W3102532606 cites W2270409809 @default.
• W3102532606 cites W2279034837 @default.
• W3102532606 cites W2335728318 @default.
• W3102532606 cites W2463241543 @default.
• W3102532606 cites W2478454054 @default.
• W3102532606 cites W2511131004 @default.
• W3102532606 cites W2562192638 @default.
• W3102532606 cites W2600030077 @default.
• W3102532606 cites W2605287558 @default.
• W3102532606 cites W2767699072 @default.
• W3102532606 cites W2785542264 @default.
• W3102532606 cites W2786559811 @default.
• W3102532606 cites W2786808285 @default.
• W3102532606 cites W2791406639 @default.
• W3102532606 cites W2795155917 @default.
• W3102532606 cites W2897345632 @default.
• W3102532606 cites W2906871406 @default.
• W3102532606 cites W2910300272 @default.
• W3102532606 cites W2920306970 @default.
• W3102532606 cites W2937073519 @default.
• W3102532606 cites W2949212125 @default.
• W3102532606 cites W2949987290 @default.
• W3102532606 cites W2951357534 @default.
• W3102532606 cites W2952267586 @default.
• W3102532606 cites W2952606116 @default.
• W3102532606 cites W2953136327 @default.
• W3102532606 cites W2953249127 @default.
• W3102532606 cites W2955889502 @default.
• W3102532606 cites W2962687275 @default.
• W3102532606 cites W2962736495 @default.
• W3102532606 cites W2963120918 @default.
• W3102532606 cites W2963124545 @default.
• W3102532606 cites W2963351448 @default.
• W3102532606 cites W2963390419 @default.
• W3102532606 cites W2969026184 @default.
• W3102532606 cites W2969329576 @default.
• W3102532606 cites W2973262547 @default.
• W3102532606 cites W2978793445 @default.
• W3102532606 cites W2981030070 @default.
• W3102532606 cites W3031262103 @default.
• W3102532606 cites W3092170595 @default.
• W3102532606 cites W3106304233 @default.
• W3102532606 cites W3132971170 @default.
• W3102532606 cites W3194006732 @default.
• W3102532606 hasPublicationYear "2020" @default.
• W3102532606 type Work @default.
• W3102532606 sameAs 3102532606 @default.
• W3102532606 citedByCount "6" @default.
• W3102532606 countsByYear W31025326062021 @default.
• W3102532606 countsByYear W31025326062022 @default.
• W3102532606 crossrefType "posted-content" @default.
• W3102532606 hasAuthorship W3102532606A5088063475 @default.
• W3102532606 hasConcept C105795698 @default.
• W3102532606 hasConcept C114614502 @default.
• W3102532606 hasConcept C119857082 @default.
• W3102532606 hasConcept C122123141 @default.
• W3102532606 hasConcept C134306372 @default.
• W3102532606 hasConcept C149441793 @default.
• W3102532606 hasConcept C150899416 @default.
• W3102532606 hasConcept C154945302 @default.
• W3102532606 hasConcept C165216359 @default.
• W3102532606 hasConcept C17744445 @default.
• W3102532606 hasConcept C190470478 @default.
• W3102532606 hasConcept C199539241 @default.
• W3102532606 hasConcept C2776359362 @default.
• W3102532606 hasConcept C33923547 @default.
• W3102532606 hasConcept C36503486 @default.
• W3102532606 hasConcept C37914503 @default.
• W3102532606 hasConcept C41008148 @default.
• W3102532606 hasConcept C43555835 @default.
• W3102532606 hasConcept C45340560 @default.
• W3102532606 hasConcept C59404180 @default.
• W3102532606 hasConcept C80444323 @default.
• W3102532606 hasConcept C83665646 @default.
• W3102532606 hasConcept C94625758 @default.
• W3102532606 hasConceptScore W3102532606C105795698 @default.
• W3102532606 hasConceptScore W3102532606C114614502 @default.
• W3102532606 hasConceptScore W3102532606C119857082 @default.
• W3102532606 hasConceptScore W3102532606C122123141 @default.
• W3102532606 hasConceptScore W3102532606C134306372 @default.
• W3102532606 hasConceptScore W3102532606C149441793 @default.
• W3102532606 hasConceptScore W3102532606C150899416 @default.
• W3102532606 hasConceptScore W3102532606C154945302 @default.
• W3102532606 hasConceptScore W3102532606C165216359 @default.
• W3102532606 hasConceptScore W3102532606C17744445 @default.
• W3102532606 hasConceptScore W3102532606C190470478 @default.

• next