mmdetection/configs/cornernet

CornerNet

Cornernet: Detecting objects as paired keypoints

Abstract

We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.2% AP on MS COCO, outperforming all existing one-stage detectors.

Results and Models

Backbone	Batch Size	Step/Total Epochs	Mem (GB)	Inf time (fps)	box AP	Config	Download
HourglassNet-104	10 x 5	180/210	13.9	4.2	41.2	config	model | log
HourglassNet-104	8 x 6	180/210	15.9	4.2	41.2	config	model | log
HourglassNet-104	32 x 3	180/210	9.5	3.9	40.4	config	model | log

Note:

• TTA setting is single-scale and flip=True. If you want to reproduce the TTA performance, please add --tta in the test command.
• Experiments with images_per_gpu=6 are conducted on Tesla V100-SXM2-32GB, images_per_gpu=3 are conducted on GeForce GTX 1080 Ti.
• Here are the descriptions of each experiment setting:
  • 10 x 5: 10 GPUs with 5 images per gpu. This is the same setting as that reported in the original paper.
  • 8 x 6: 8 GPUs with 6 images per gpu. The total batchsize is similar to paper and only need 1 node to train.
  • 32 x 3: 32 GPUs with 3 images per gpu. The default setting for 1080TI and need 4 nodes to train.

Citation

@inproceedings{law2018cornernet,
  title={Cornernet: Detecting objects as paired keypoints},
  author={Law, Hei and Deng, Jia},
  booktitle={15th European Conference on Computer Vision, ECCV 2018},
  pages={765--781},
  year={2018},
  organization={Springer Verlag}
}