Entity The code on Ade20k

Thanks for your great work "Open-World Entity Segmentation". Could you provide the evaluation code on ADE-20K dataset, when using models trained on COCO?

Feb 19 '22 06:02 Yinyf0804

We use the class-agnostic COCO API to evaluate both COCO and ADE20K. Thus, you could only transform the ADE20K annotation format to COCO annotation format.

Feb 21 '22 02:02 qqlu

Thanks for your advice. I use the model trained on COCO (r50 1x 29.8) and evaluate it on ADE20K val, get the results 20.09 box AP and 13.78 seg AP. So i wonder if the AP box are used as AP_e in Table4(a) ?

Feb 22 '22 06:02 Yinyf0804

We still use AP_e to evaluate ADE20K. At first, we use 3x models in Table4(a). Second, we clear some annotations in ADE20K to keep consistency with COCO. That's because the definitions of COCO and ADE20K for things and stuff are different. This part of the code should be released after the acceptance of the paper.

It is also a weakness of our paper that the annotation should be kreept consistent among different datasets. We are solving this problem in another way.

Feb 22 '22 06:02 qqlu

Thanks for your reply. But the caption of Table4 mentions that "(3) Ours with 12 epochs in (a)", and Sec 6.2 mentions that "PanopticFCN and DETR are trained for 12 and 300 epochs". I wonder if you actually use 1x models in Table4(a)?

Feb 24 '22 13:02 Yinyf0804