Cascade Mask R-CNN

open-mmlab / mmdetection

Last updated on Feb 23, 2021
Cascade Mask R-CNN (R-101-FPN, 1x, caffe)
Memory (M) 7800.0
Backbone Layers 101
File Size 367.95 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, Dense Connections, FPN, ResNet, RoIAlign
lr sched 1x
Memory (M) 7800.0
Backbone Layers 101
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (R-101-FPN, 1x, pytorch)
Memory (M) 7900.0
inference time (s/im) 0.10204
File Size 367.94 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, Dense Connections, FPN, ResNet, RoIAlign
lr sched 1x
Memory (M) 7900.0
Backbone Layers 101
inference time (s/im) 0.10204
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (R-101-FPN, 20e, pytorch)
lr sched 20e
Backbone Layers 101
File Size 367.95 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, Dense Connections, FPN, ResNet, RoIAlign
lr sched 20e
Backbone Layers 101
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (R-50-FPN, 1x, caffe)
Memory (M) 5900.0
Backbone Layers 50
File Size 295.25 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, Dense Connections, FPN, ResNet, RoIAlign
lr sched 1x
Memory (M) 5900.0
Backbone Layers 50
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (R-50-FPN, 1x, pytorch)
Memory (M) 6000.0
inference time (s/im) 0.08929
File Size 295.24 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, Dense Connections, FPN, ResNet, RoIAlign
lr sched 1x
Memory (M) 6000.0
Backbone Layers 50
inference time (s/im) 0.08929
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (R-50-FPN, 20e, pytorch)
lr sched 20e
Backbone Layers 50
File Size 295.25 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, Dense Connections, FPN, ResNet, RoIAlign
lr sched 20e
Backbone Layers 50
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (X-101-32x4d-FPN, 1x, pytorch)
Memory (M) 9200.0
inference time (s/im) 0.11628
File Size 366.65 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, Dense Connections, FPN, RoIAlign
lr sched 1x
Memory (M) 9200.0
Backbone Layers 101
inference time (s/im) 0.11628
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (X-101-32x4d-FPN, 20e, pytorch)
Memory (M) 9200.0
Backbone Layers 101
File Size 366.65 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, Dense Connections, FPN, RoIAlign
lr sched 20e
Memory (M) 9200.0
Backbone Layers 101
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (X-101-64x4d-FPN, 1x, pytorch)
Memory (M) 12200.0
inference time (s/im) 0.14925
File Size 516.73 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, Dense Connections, FPN, RoIAlign
lr sched 1x
Memory (M) 12200.0
Backbone Layers 101
inference time (s/im) 0.14925
SHOW MORE
SHOW LESS
Cascade Mask R-CNN (X-101-64x4d-FPN, 20e, pytorch)
Memory (M) 12200.0
Backbone Layers 101
File Size 516.73 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, Dense Connections, FPN, RoIAlign
lr sched 20e
Memory (M) 12200.0
Backbone Layers 101
SHOW MORE
SHOW LESS
README.md

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

Introduction

[ALGORITHM]

@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.

Results

Object Detection on COCO minival

Object Detection on COCO minival
MODEL BOX AP
Cascade Mask R-CNN (X-101-64x4d-FPN, 20e, pytorch) 45.6
Cascade Mask R-CNN (X-101-64x4d-FPN, 1x, pytorch) 45.3
Cascade Mask R-CNN (X-101-32x4d-FPN, 20e, pytorch) 45.0
Cascade Mask R-CNN (X-101-32x4d-FPN, 1x, pytorch) 44.3
Cascade Mask R-CNN (R-101-FPN, 20e, pytorch) 43.4
Cascade Mask R-CNN (R-101-FPN, 1x, caffe) 43.2
Cascade Mask R-CNN (R-101-FPN, 1x, pytorch) 42.9
Cascade Mask R-CNN (R-50-FPN, 20e, pytorch) 41.9
Cascade Mask R-CNN (R-50-FPN, 1x, caffe) 41.2
Cascade Mask R-CNN (R-50-FPN, 1x, pytorch) 41.2
Instance Segmentation on COCO minival
MODEL MASK AP
Cascade Mask R-CNN (X-101-64x4d-FPN, 20e, pytorch) 39.5
Cascade Mask R-CNN (X-101-64x4d-FPN, 1x, pytorch) 39.2
Cascade Mask R-CNN (X-101-32x4d-FPN, 20e, pytorch) 39.0
Cascade Mask R-CNN (X-101-32x4d-FPN, 1x, pytorch) 38.3
Cascade Mask R-CNN (R-101-FPN, 20e, pytorch) 37.8
Cascade Mask R-CNN (R-101-FPN, 1x, caffe) 37.6
Cascade Mask R-CNN (R-101-FPN, 1x, pytorch) 37.3
Cascade Mask R-CNN (R-50-FPN, 20e, pytorch) 36.5
Cascade Mask R-CNN (R-50-FPN, 1x, caffe) 36.0
Cascade Mask R-CNN (R-50-FPN, 1x, pytorch) 35.9
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy