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	Download
R-50-FPN	caffe	1x	4.2		40.4	model | log
R-50-FPN	pytorch	1x	4.4	16.1	40.3	model | log
R-50-FPN	pytorch	20e	-	-	41.0	model | log
R-101-FPN	caffe	1x	6.2		42.3	model | log
R-101-FPN	pytorch	1x	6.4	13.5	42.0	model | log
R-101-FPN	pytorch	20e	-	-	42.5	model | log
X-101-32x4d-FPN	pytorch	1x	7.6	10.9	43.7	model | log
X-101-32x4d-FPN	pytorch	20e	7.6		43.7	model | log
X-101-64x4d-FPN	pytorch	1x	10.7		44.7	model | log
X-101-64x4d-FPN	pytorch	20e	10.7		44.5	model | log

Cascade Mask R-CNN

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