Skip to content

Latest commit

 

History

History
51 lines (39 loc) · 3.55 KB

README.md

File metadata and controls

51 lines (39 loc) · 3.55 KB

SCNet

Introduction

We provide the code for reproducing experiment results of SCNet.

@inproceedings{vu2019cascade,
  title={SCNet: Training Inference Sample Consistency for Instance Segmentation},
  author={Vu, Thang and Haeyong, Kang and Yoo, Chang D},
  booktitle={AAAI},
  year={2021}
}

Dataset

SCNet requires COCO and COCO-stuff dataset for training. You need to download and extract it in the COCO dataset path. The directory should be like this.

mmdetection
├── mmdet
├── tools
├── configs
├── data
│   ├── coco
│   │   ├── annotations
│   │   ├── train2017
│   │   ├── val2017
│   │   ├── test2017
|   |   ├── stuffthingmaps

Results and Models

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

Backbone Style Lr schd Mem (GB) Inf speed (fps) box AP mask AP TTA box AP TTA mask AP Config Download
R-50-FPN pytorch 1x 7.0 6.2 43.5 39.2 44.8 40.9 config model | log
R-50-FPN pytorch 20e 7.0 6.2 44.5 40.0 45.8 41.5 config model | log
R-101-FPN pytorch 20e 8.9 5.8 45.8 40.9 47.3 42.7 config model | log
X-101-64x4d-FPN pytorch 20e 13.2 4.9 47.5 42.3 48.9 44.0 config model | log

Notes

  • Training hyper-parameters are identical to those of HTC.
  • TTA means Test Time Augmentation, which applies horizontal flip and multi-scale testing. Refer to config.