Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893671576> ?p ?o ?g. }
- W2893671576 abstract "Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the model on labeled synthetic datasets and apply it in the real scenes. However, this straightforward method often fails to generalize well mainly due to the domain bias between the synthetic and real datasets. Many unsupervised domain adaptation (UDA) methods are introduced to address this problem but most of them only focus on the simple classification task. In this paper, we present a novel UDA model to solve the more complex object detection problem in the context of autonomous driving. Our model integrates both pixel level and feature level based transformtions to fulfill the cross domain detection task and can be further trained end-to-end to pursue better performance. We employ objectives of the generative adversarial network and the cycle consistency loss for image translation in the pixel space. To address the potential semantic inconsistency problem, we propose region proposal based feature adversarial training to preserve the semantics of our target objects as well as further minimize the domain shifts. Extensive experiments are conducted on several different datasets, and the results demonstrate the robustness and superiority of our method." @default.
- W2893671576 created "2018-10-05" @default.
- W2893671576 creator A5004661311 @default.
- W2893671576 creator A5010686710 @default.
- W2893671576 creator A5073468340 @default.
- W2893671576 date "2018-09-30" @default.
- W2893671576 modified "2023-09-27" @default.
- W2893671576 title "Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving" @default.
- W2893671576 cites W1536680647 @default.
- W2893671576 cites W1686810756 @default.
- W2893671576 cites W1731081199 @default.
- W2893671576 cites W1901129140 @default.
- W2893671576 cites W2096943734 @default.
- W2893671576 cites W2097117768 @default.
- W2893671576 cites W2099471712 @default.
- W2893671576 cites W2102605133 @default.
- W2893671576 cites W2104094955 @default.
- W2893671576 cites W2115403315 @default.
- W2893671576 cites W2115579991 @default.
- W2893671576 cites W2121058967 @default.
- W2893671576 cites W2128053425 @default.
- W2893671576 cites W2131953535 @default.
- W2893671576 cites W2159291411 @default.
- W2893671576 cites W2163605009 @default.
- W2893671576 cites W2164587673 @default.
- W2893671576 cites W2164943005 @default.
- W2893671576 cites W2184188583 @default.
- W2893671576 cites W2194775991 @default.
- W2893671576 cites W2279034837 @default.
- W2893671576 cites W2331128040 @default.
- W2893671576 cites W2340897893 @default.
- W2893671576 cites W2397830550 @default.
- W2893671576 cites W2407521645 @default.
- W2893671576 cites W2475287302 @default.
- W2893671576 cites W2511131004 @default.
- W2893671576 cites W2579985080 @default.
- W2893671576 cites W2584009249 @default.
- W2893671576 cites W2593768305 @default.
- W2893671576 cites W2606831796 @default.
- W2893671576 cites W2613718673 @default.
- W2893671576 cites W2796347433 @default.
- W2893671576 cites W2803732898 @default.
- W2893671576 cites W2804403376 @default.
- W2893671576 cites W2895236117 @default.
- W2893671576 cites W2903052031 @default.
- W2893671576 cites W2949848065 @default.
- W2893671576 cites W2962793481 @default.
- W2893671576 cites W2962808524 @default.
- W2893671576 cites W2963073614 @default.
- W2893671576 cites W2963275094 @default.
- W2893671576 cites W2963330667 @default.
- W2893671576 cites W2963784072 @default.
- W2893671576 cites W2963815055 @default.
- W2893671576 cites W2963826681 @default.
- W2893671576 cites W2964115968 @default.
- W2893671576 cites W3106250896 @default.
- W2893671576 hasPublicationYear "2018" @default.
- W2893671576 type Work @default.
- W2893671576 sameAs 2893671576 @default.
- W2893671576 citedByCount "3" @default.
- W2893671576 countsByYear W28936715762018 @default.
- W2893671576 countsByYear W28936715762019 @default.
- W2893671576 countsByYear W28936715762020 @default.
- W2893671576 crossrefType "posted-content" @default.
- W2893671576 hasAuthorship W2893671576A5004661311 @default.
- W2893671576 hasAuthorship W2893671576A5010686710 @default.
- W2893671576 hasAuthorship W2893671576A5073468340 @default.
- W2893671576 hasConcept C104317684 @default.
- W2893671576 hasConcept C115961682 @default.
- W2893671576 hasConcept C119857082 @default.
- W2893671576 hasConcept C120665830 @default.
- W2893671576 hasConcept C121332964 @default.
- W2893671576 hasConcept C134306372 @default.
- W2893671576 hasConcept C138885662 @default.
- W2893671576 hasConcept C153180895 @default.
- W2893671576 hasConcept C154945302 @default.
- W2893671576 hasConcept C160633673 @default.
- W2893671576 hasConcept C185592680 @default.
- W2893671576 hasConcept C192209626 @default.
- W2893671576 hasConcept C2776151529 @default.
- W2893671576 hasConcept C2776401178 @default.
- W2893671576 hasConcept C2779757391 @default.
- W2893671576 hasConcept C33923547 @default.
- W2893671576 hasConcept C36503486 @default.
- W2893671576 hasConcept C37736160 @default.
- W2893671576 hasConcept C41008148 @default.
- W2893671576 hasConcept C41895202 @default.
- W2893671576 hasConcept C55493867 @default.
- W2893671576 hasConcept C63479239 @default.
- W2893671576 hasConcept C81363708 @default.
- W2893671576 hasConceptScore W2893671576C104317684 @default.
- W2893671576 hasConceptScore W2893671576C115961682 @default.
- W2893671576 hasConceptScore W2893671576C119857082 @default.
- W2893671576 hasConceptScore W2893671576C120665830 @default.
- W2893671576 hasConceptScore W2893671576C121332964 @default.
- W2893671576 hasConceptScore W2893671576C134306372 @default.
- W2893671576 hasConceptScore W2893671576C138885662 @default.
- W2893671576 hasConceptScore W2893671576C153180895 @default.
- W2893671576 hasConceptScore W2893671576C154945302 @default.
- W2893671576 hasConceptScore W2893671576C160633673 @default.