Guided Anchoring

open-mmlab / mmdetection

Last updated on Feb 23, 2021
GA-Faster R-CNN (R-101-FPN, 1x, caffe)
Memory (M) 7500.0
Backbone Layers 101
File Size 234.48 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, Guided Anchoring, FPN, RoIPool, ResNet
lr sched 1x
Memory (M) 7500.0
Backbone Layers 101
SHOW MORE
SHOW LESS
GA-Faster R-CNN (R-50-FPN, 1x, caffe)
Memory (M) 5500.0
Backbone Layers 50
File Size 161.79 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, Guided Anchoring, FPN, RoIPool, ResNet
lr sched 1x
Memory (M) 5500.0
Backbone Layers 50
SHOW MORE
SHOW LESS
GA-Faster R-CNN (X-101-32x4d-FPN, 1x, pytorch)
Memory (M) 8700.0
inference time (s/im) 0.10309
File Size 233.19 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, Guided Anchoring, FPN, RoIPool
lr sched 1x
Memory (M) 8700.0
Backbone Layers 101
inference time (s/im) 0.10309
SHOW MORE
SHOW LESS
GA-Faster R-CNN (X-101-64x4d-FPN, 1x, pytorch)
Memory (M) 11800.0
inference time (s/im) 0.13699
File Size 383.27 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, Guided Anchoring, FPN, RoIPool
lr sched 1x
Memory (M) 11800.0
Backbone Layers 101
inference time (s/im) 0.13699
SHOW MORE
SHOW LESS
GA-RetinaNet (R-101-FPN, 1x, caffe)
Memory (M) 5500.0
inference time (s/im) 0.07752
File Size 216.40 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture RPN, Guided Anchoring, FPN, ResNet, Focal Loss
lr sched 1x
Memory (M) 5500.0
Backbone Layers 101
inference time (s/im) 0.07752
SHOW MORE
SHOW LESS
GA-RetinaNet (R-50-FPN, 1x, caffe)
Memory (M) 3500.0
inference time (s/im) 0.05952
File Size 143.70 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture RPN, Guided Anchoring, FPN, ResNet, Focal Loss
lr sched 1x
Memory (M) 3500.0
Backbone Layers 50
inference time (s/im) 0.05952
SHOW MORE
SHOW LESS
GA-RetinaNet (X-101-32x4d-FPN, 1x, pytorch)
Memory (M) 6900.0
inference time (s/im) 0.09434
File Size 215.10 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture RPN, ResNeXt, Guided Anchoring, FPN, Focal Loss
lr sched 1x
Memory (M) 6900.0
Backbone Layers 101
inference time (s/im) 0.09434
SHOW MORE
SHOW LESS
GA-RetinaNet (X-101-64x4d-FPN, 1x, pytorch)
Memory (M) 9900.0
inference time (s/im) 0.12987
File Size 365.18 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture RPN, ResNeXt, Guided Anchoring, FPN, Focal Loss
lr sched 1x
Memory (M) 9900.0
Backbone Layers 101
inference time (s/im) 0.12987
SHOW MORE
SHOW LESS
README.md

Region Proposal by Guided Anchoring

Introduction

[ALGORITHM]

We provide config files to reproduce the results in the CVPR 2019 paper for Region Proposal by Guided Anchoring.

@inproceedings{wang2019region,
    title={Region Proposal by Guided Anchoring},
    author={Jiaqi Wang and Kai Chen and Shuo Yang and Chen Change Loy and Dahua Lin},
    booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
    year={2019}
}

Results and Models

The results on COCO 2017 val is shown in the below table. (results on test-dev are usually slightly higher than val).

Method Backbone Style Lr schd Mem (GB) Inf time (fps) AR 1000 Config Download
GA-RPN R-50-FPN caffe 1x 5.3 15.8 68.4 config model | log
GA-RPN R-101-FPN caffe 1x 7.3 13.0 69.5 config model | log
GA-RPN X-101-32x4d-FPN pytorch 1x 8.5 10.0 70.6 config model | log
GA-RPN X-101-64x4d-FPN pytorch 1x 7.1 7.5 71.2 config model | log
Method Backbone Style Lr schd Mem (GB) Inf time (fps) box AP Config Download
GA-Faster RCNN R-50-FPN caffe 1x 5.5 39.6 config model | log
GA-Faster RCNN R-101-FPN caffe 1x 7.5 41.5 config model | log
GA-Faster RCNN X-101-32x4d-FPN pytorch 1x 8.7 9.7 43.0 config model | log
GA-Faster RCNN X-101-64x4d-FPN pytorch 1x 11.8 7.3 43.9 config model | log
GA-RetinaNet R-50-FPN caffe 1x 3.5 16.8 36.9 config model | log
GA-RetinaNet R-101-FPN caffe 1x 5.5 12.9 39.0 config model | log
GA-RetinaNet X-101-32x4d-FPN pytorch 1x 6.9 10.6 40.5 config model | log
GA-RetinaNet X-101-64x4d-FPN pytorch 1x 9.9 7.7 41.3 config model | log

  • In the Guided Anchoring paper, score_thr is set to 0.001 in Fast/Faster RCNN and 0.05 in RetinaNet for both baselines and Guided Anchoring.

  • Performance on COCO test-dev benchmark are shown as follows.

Method Backbone Style Lr schd Aug Train Score thr AP AP_50 AP_75 AP_small AP_medium AP_large Download
GA-Faster RCNN R-101-FPN caffe 1x F 0.05
GA-Faster RCNN R-101-FPN caffe 1x F 0.001
GA-RetinaNet R-101-FPN caffe 1x F 0.05
GA-RetinaNet R-101-FPN caffe 2x T 0.05

Results

Object Detection on COCO minival

Object Detection on COCO minival
MODEL BOX AP
GA-Faster R-CNN (X-101-64x4d-FPN, 1x, pytorch) 43.9
GA-Faster R-CNN (X-101-32x4d-FPN, 1x, pytorch) 43.0
GA-Faster R-CNN (R-101-FPN, 1x, caffe) 41.5
GA-RetinaNet (X-101-64x4d-FPN, 1x, pytorch) 41.3
GA-RetinaNet (X-101-32x4d-FPN, 1x, pytorch) 40.5
GA-Faster R-CNN (R-50-FPN, 1x, caffe) 39.6
GA-RetinaNet (R-101-FPN, 1x, caffe) 39.0
GA-RetinaNet (R-50-FPN, 1x, caffe) 36.9
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