Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134562213> ?p ?o ?g. }
- W3134562213 abstract "We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object scaling strategy for mitigating the negative effects of source domain bias. Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory bank and the model training with curriculum data augmentation. These specific designs for 3D object detection enable the detector to be trained with consistent and high-quality pseudo labels and to avoid overfitting to the large number of easy examples in pseudo labeled data. Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark. Code will be available at https://github.com/CVMI-Lab/ST3D." @default.
- W3134562213 created "2021-03-15" @default.
- W3134562213 creator A5048895819 @default.
- W3134562213 creator A5056053058 @default.
- W3134562213 creator A5065073978 @default.
- W3134562213 creator A5075014670 @default.
- W3134562213 creator A5083443210 @default.
- W3134562213 date "2021-03-09" @default.
- W3134562213 modified "2023-09-26" @default.
- W3134562213 title "ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection" @default.
- W3134562213 cites W1522301498 @default.
- W3134562213 cites W1836465849 @default.
- W3134562213 cites W2045724293 @default.
- W3134562213 cites W2099471712 @default.
- W3134562213 cites W2150066425 @default.
- W3134562213 cites W2156557681 @default.
- W3134562213 cites W2159291411 @default.
- W3134562213 cites W2296073425 @default.
- W3134562213 cites W2555618208 @default.
- W3134562213 cites W2562192638 @default.
- W3134562213 cites W2594718649 @default.
- W3134562213 cites W2767657961 @default.
- W3134562213 cites W2792643794 @default.
- W3134562213 cites W2795155917 @default.
- W3134562213 cites W2798965597 @default.
- W3134562213 cites W2895281799 @default.
- W3134562213 cites W2897529137 @default.
- W3134562213 cites W2900234507 @default.
- W3134562213 cites W2919534447 @default.
- W3134562213 cites W2920326761 @default.
- W3134562213 cites W2945328857 @default.
- W3134562213 cites W2949708697 @default.
- W3134562213 cites W2962687275 @default.
- W3134562213 cites W2962912109 @default.
- W3134562213 cites W2963121255 @default.
- W3134562213 cites W2963150697 @default.
- W3134562213 cites W2963400571 @default.
- W3134562213 cites W2963481481 @default.
- W3134562213 cites W2963727135 @default.
- W3134562213 cites W2963826681 @default.
- W3134562213 cites W2964115968 @default.
- W3134562213 cites W2966743431 @default.
- W3134562213 cites W2968296999 @default.
- W3134562213 cites W2968634921 @default.
- W3134562213 cites W2970623619 @default.
- W3134562213 cites W2979548969 @default.
- W3134562213 cites W2981705647 @default.
- W3134562213 cites W2981949127 @default.
- W3134562213 cites W2982204955 @default.
- W3134562213 cites W2985406498 @default.
- W3134562213 cites W2995681297 @default.
- W3134562213 cites W2995852213 @default.
- W3134562213 cites W2997643725 @default.
- W3134562213 cites W2998607115 @default.
- W3134562213 cites W3034140121 @default.
- W3134562213 cites W3034602892 @default.
- W3134562213 cites W3034975685 @default.
- W3134562213 cites W3035160371 @default.
- W3134562213 cites W3035172746 @default.
- W3134562213 cites W3035574168 @default.
- W3134562213 cites W3035750252 @default.
- W3134562213 cites W3043274762 @default.
- W3134562213 cites W3047032303 @default.
- W3134562213 cites W3095253761 @default.
- W3134562213 cites W3126960890 @default.
- W3134562213 cites W3127310617 @default.
- W3134562213 doi "https://doi.org/10.48550/arxiv.2103.05346" @default.
- W3134562213 hasPublicationYear "2021" @default.
- W3134562213 type Work @default.
- W3134562213 sameAs 3134562213 @default.
- W3134562213 citedByCount "1" @default.
- W3134562213 countsByYear W31345622132021 @default.
- W3134562213 crossrefType "posted-content" @default.
- W3134562213 hasAuthorship W3134562213A5048895819 @default.
- W3134562213 hasAuthorship W3134562213A5056053058 @default.
- W3134562213 hasAuthorship W3134562213A5065073978 @default.
- W3134562213 hasAuthorship W3134562213A5075014670 @default.
- W3134562213 hasAuthorship W3134562213A5083443210 @default.
- W3134562213 hasBestOaLocation W31345622131 @default.
- W3134562213 hasConcept C119857082 @default.
- W3134562213 hasConcept C120665830 @default.
- W3134562213 hasConcept C121332964 @default.
- W3134562213 hasConcept C131979681 @default.
- W3134562213 hasConcept C13280743 @default.
- W3134562213 hasConcept C134306372 @default.
- W3134562213 hasConcept C139807058 @default.
- W3134562213 hasConcept C153180895 @default.
- W3134562213 hasConcept C154945302 @default.
- W3134562213 hasConcept C177264268 @default.
- W3134562213 hasConcept C185798385 @default.
- W3134562213 hasConcept C199360897 @default.
- W3134562213 hasConcept C205649164 @default.
- W3134562213 hasConcept C22019652 @default.
- W3134562213 hasConcept C2776151529 @default.
- W3134562213 hasConcept C2776760102 @default.
- W3134562213 hasConcept C2781238097 @default.
- W3134562213 hasConcept C31972630 @default.
- W3134562213 hasConcept C33923547 @default.
- W3134562213 hasConcept C36503486 @default.
- W3134562213 hasConcept C41008148 @default.