DJW c16313bb6a 第一次提交 | 9 hónapja | |
---|---|---|
.. | ||
README.md | 9 hónapja | |
cornernet_hourglass104_10xb5-crop511-210e-mstest_coco.py | 9 hónapja | |
cornernet_hourglass104_32xb3-210e-mstest_coco.py | 9 hónapja | |
cornernet_hourglass104_8xb6-210e-mstest_coco.py | 9 hónapja | |
metafile.yml | 9 hónapja |
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.
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:
flip=True
. If you want to reproduce the TTA performance, please add --tta
in the test command.images_per_gpu=6
are conducted on Tesla V100-SXM2-32GB, images_per_gpu=3
are conducted on GeForce GTX 1080 Ti.@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}
}