Part-aware Panoptic Segmentation

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

In this work, we introduce the new scene understanding task of Part-aware Panoptic Segmentation (PPS), which aims to understand a scene at multiple levels of abstraction, and unifies the tasks of scene parsing and part parsing. For this novel task, we provide consistent annotations on two commonly used datasets: Cityscapes and Pascal VOC. Moreover, we present a single metric to evaluate PPS, called Part-aware Panoptic Quality (PartPQ). For this new task, using the metric and annotations, we set multiple baselines by merging results of existing state-of-the-art methods for panoptic segmentation and part segmentation. Finally, we conduct several experiments that evaluate the importance of the different levels of abstraction in this single task.
Originele taal-2Engels
Titel2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's5481-5490
Aantal pagina's10
ISBN van elektronische versie978-1-6654-4509-2
DOI's
StatusGepubliceerd - 13 nov 2021
Evenement2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Nashville, Verenigde Staten van Amerika
Duur: 19 jun 202125 jun 2021

Congres

Congres2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
Verkorte titelCVPRW 2021
Land/RegioVerenigde Staten van Amerika
StadNashville
Periode19/06/2125/06/21

Vingerafdruk

Duik in de onderzoeksthema's van 'Part-aware Panoptic Segmentation'. Samen vormen ze een unieke vingerafdruk.

Citeer dit