LVIS dataset

Introduction

@inproceedings{gupta2019lvis,
  title={{LVIS}: A Dataset for Large Vocabulary Instance Segmentation},
  author={Gupta, Agrim and Dollar, Piotr and Girshick, Ross},
  booktitle={Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition},
  year={2019}
}

Common Setting

• Please follow install guide to install open-mmlab forked cocoapi first.
• Run following scripts to install our forked lvis-api.

  # mmlvis is fully compatible with official lvis
  pip install mmlvis
  

  or

  pip install -r requirements/optional.txt
  

• All experiments use oversample strategy here with oversample threshold 1e-3.
• The size of LVIS v0.5 is half of COCO, so schedule 2x in LVIS is roughly the same iterations as 1x in COCO.

Results and models of LVIS v0.5

Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Config	Download
R-50-FPN	pytorch	2x	-	-	26.1	25.9	config	model | log
R-101-FPN	pytorch	2x	-	-	27.1	27.0	config	model | log
X-101-32x4d-FPN	pytorch	2x	-	-	26.7	26.9	config	model | log
X-101-64x4d-FPN	pytorch	2x	-	-	26.4	26.0	config	model | log

Results and models of LVIS v1

Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Config	Download
R-50-FPN	pytorch	1x	9.1	-	22.5	21.7	config	model | log
R-101-FPN	pytorch	1x	10.8	-	24.6	23.6	config	model | log
X-101-32x4d-FPN	pytorch	1x	11.8	-	26.7	25.5	config	model | log
X-101-64x4d-FPN	pytorch	1x	14.6	-	27.2	25.8	config	model | log