Point Cloud Instance Segmentation With Semi-Supervised Bounding-Box Mining

Point Cloud Instance Segmentation With Semi-Supervised Bounding-Box Mining

Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud annotations. To alleviate the annotation cost, unlabeled or weakly labeled data is still less explored...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 12 vom: 03. Dez., Seite 10159-10170
1. Verfasser: Liao, Yongbin (VerfasserIn)
Weitere Verfasser: Zhu, Hongyuan, Zhang, Yanggang, Ye, Chuangguan, Chen, Tao, Fan, Jiayuan
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM333840054
003 DE-627
005 20231225222455.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2021.3131120  |2 doi 
028 5 2 |a pubmed24n1112.xml 
035 |a (DE-627)NLM333840054 
035 |a (NLM)34847018 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Liao, Yongbin  |e verfasserin  |4 aut 
245 1 0 |a Point Cloud Instance Segmentation With Semi-Supervised Bounding-Box Mining 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 08.11.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud annotations. To alleviate the annotation cost, unlabeled or weakly labeled data is still less explored in the task. In this paper, we introduce the first semi-supervised point cloud instance segmentation framework (SPIB) using both labeled and unlabelled bounding boxes as supervision. To be specific, our SPIB architecture involves a two-stage learning procedure. For stage one, a bounding box proposal generation network is trained under a semi-supervised setting with perturbation consistency regularization (SPCR). The regularization works by enforcing an invariance of the bounding box predictions over different perturbations applied to the input point clouds, to provide self-supervision for network learning. For stage two, the bounding box proposals with SPCR are grouped into some subsets, and the instance masks are mined inside each subset with a novel semantic propagation module and a property consistency graph module. Moreover, we introduce a novel occupancy ratio guided refinement module to refine the instance masks. Extensive experiments on the challenging ScanNet v2 dataset demonstrate our method can achieve competitive performance compared with the recent fully-supervised methods 
650 4 |a Journal Article 
700 1 |a Zhu, Hongyuan  |e verfasserin  |4 aut 
700 1 |a Zhang, Yanggang  |e verfasserin  |4 aut 
700 1 |a Ye, Chuangguan  |e verfasserin  |4 aut 
700 1 |a Chen, Tao  |e verfasserin  |4 aut 
700 1 |a Fan, Jiayuan  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 44(2022), 12 vom: 03. Dez., Seite 10159-10170  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:44  |g year:2022  |g number:12  |g day:03  |g month:12  |g pages:10159-10170 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2021.3131120  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 44  |j 2022  |e 12  |b 03  |c 12  |h 10159-10170