Evaluation Metric
In the challenge, we use Average Precision (AP) as the evaluation metric，which is same with the coco competition.
| Metric | Description |
|---|---|
| Average Precision (AP): | |
| AP | % AP at IoU=.50:.05:.95 (primary challenge metric) |
| APIoU=.50 | % AP at IoU=.50 (PASCAL VOC metric) |
| APIoU=.75 | % AP at IoU=.75 (strict metric) |
| AP Across Scales: | |
| APsmall | % AP for small objects: area < 322 |
| APmedium | % AP for medium objects: 322 < area < 962 |
| APlarge | % AP for large objects: area > 962 |
| Average Recall (AR): | |
| ARmax=1 | % AR given 1 detection per image |
| ARmax=10 | % AR given 10 detections per image |
| ARmax=100 | % AR given 100 detections per image |
| AR Across Scales: | |
| ARsmall | % AR for small objects: area < 322 |
| ARmedium | % AR for medium objects: 322 < area < 962 |
| ARlarge | % AR for large objects: area > 962 |
Format of Submission
To submit your result, you are required to submit a .json file. WE follow the format of COCO.
Format of Filenames
After processing the input images of the validation set, you should save the results as:
lis_coco_png_raw_dark_valonly_challenge.json
After processing the input images of the testing set, you should save the results as:
lis_coco_png_raw_dark_testonly_challenge.json
You should directly save the JSON file corresponding to the results you want to submit in a folder. There should be no other folders within the path. Before submission, compress the folder into a zip file.
Submission