Published June 18, 2022 | Version V1.0

FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing

  • 1. Google Research
  • 2. IIIT Hyderabad

Description

Pascal-Part-201 is the most comprehensive and challenging version of the Pascal-Part dataset for Multi-object multi-part scene parsing. The dataset is the part of the publication "FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing" published in CVPR 2022.

Files

dataset_readme.pdf

Files (3.4 GB)

Name Size
md5:4152b74fe721de924f5977016216b555
85.6 kB Preview Download
md5:af5d890d21735b7c4a74477fc2a6f2e4
3.4 GB Preview Download