VOC annotations generated by maskcut
zqwang21 opened this issue · comments
Hey, this is my jsonfile for VOC annoatations generated by maskcut ,but the bbox information is different from the file you submitted in github. Therefore I visualize the results of both of us on JPEGImages/009829.jpg ,the yellow boxes are mine and the red are yours.
Do you have any idea why there are these differences?
voc_annotations.zip
Hi, the JSON file we provided contains ground truth annotations that have been converted to COCO-style format. The main purpose of providing this file is to evaluate the zero-shot unsupervised detection performance of our model. Also, the coco-style bounding box format should be [x_min, y_min, width, height], which is different from the voc format. Hope it helps!