Skip to content

Latest commit

 

History

History
69 lines (56 loc) · 16.7 KB

README.md

File metadata and controls

69 lines (56 loc) · 16.7 KB
Raw

Cascade R-CNN: High Quality Object Detection and Instance Segmentation

Introduction

@article{Cai_2019,
   title={Cascade R-CNN: High Quality Object Detection and Instance Segmentation},
   ISSN={1939-3539},
   url={http://dx.doi.org/10.1109/tpami.2019.2956516},
   DOI={10.1109/tpami.2019.2956516},
   journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Cai, Zhaowei and Vasconcelos, Nuno},
   year={2019},
   pages={1–1}
}

Results and models

Cascade R-CNN

Backbone Style Lr schd Mem (GB) Inf time (fps) box AP Config Download
R-50-FPN caffe 1x 4.2 40.4 config model | log
R-50-FPN pytorch 1x 4.4 16.1 40.3 config model | log
R-50-FPN pytorch 20e - - 41.0 config model | log
R-101-FPN caffe 1x 6.2 42.3 config model | log
R-101-FPN pytorch 1x 6.4 13.5 42.0 config model | log
R-101-FPN pytorch 20e - - 42.5 config model | log
X-101-32x4d-FPN pytorch 1x 7.6 10.9 43.7 config model | log
X-101-32x4d-FPN pytorch 20e 7.6 43.7 config model | log
X-101-64x4d-FPN pytorch 1x 10.7 44.7 config model | log
X-101-64x4d-FPN pytorch 20e 10.7 44.5 config model | log

Cascade Mask R-CNN

Backbone Style Lr schd Mem (GB) Inf time (fps) box AP mask AP Config Download
R-50-FPN caffe 1x 5.9 41.2 36.0 config model | log
R-50-FPN pytorch 1x 6.0 11.2 41.2 35.9 config model | log
R-50-FPN pytorch 20e - - 41.9 36.5 config model | log
R-101-FPN caffe 1x 7.8 43.2 37.6 config model | log
R-101-FPN pytorch 1x 7.9 9.8 42.9 37.3 config model | log
R-101-FPN pytorch 20e - - 43.4 37.8 config model | log
X-101-32x4d-FPN pytorch 1x 9.2 8.6 44.3 38.3 config model | log
X-101-32x4d-FPN pytorch 20e 9.2 - 45.0 39.0 config model | log
X-101-64x4d-FPN pytorch 1x 12.2 6.7 45.3 39.2 config model | log
X-101-64x4d-FPN pytorch 20e 12.2 45.6 39.5 config model | log

Notes:

  • The 20e schedule in Cascade (Mask) R-CNN indicates decreasing the lr at 16 and 19 epochs, with a total of 20 epochs.

Pre-trained Models

We also train some models with longer schedules and multi-scale training for Cascade Mask R-CNN. The users could finetune them for downstream tasks.

Backbone Style Lr schd Mem (GB) Inf time (fps) box AP mask AP Config Download
R-50-FPN caffe 3x 5.7 44.0 38.1 config model | log
R-50-FPN pytorch 3x 5.9 44.3 38.5 config model | log
R-101-FPN caffe 3x 7.7 45.4 39.5 config model | log
R-101-FPN pytorch 3x 7.8 45.5 39.6 config model | log
X-101-32x4d-FPN pytorch 3x 9.0 46.3 40.1 config model | log
X-101-32x8d-FPN pytorch 3x 12.1 46.1 39.9 config model | log
X-101-64x4d-FPN pytorch 3x 12.0 46.6 40.3 config model | log