What's the difference between the models used in davis17 and youtubevos when evaluation

z-x-yang / CFBI

The official implementation of CFBI(+): Collaborative Video Object Segmentation by (Multi-scale) Foreground-Background Integration.

BSD 3-Clause "New" or "Revised" License

322 stars 43 forks source link

What's the difference between the models used in davis17 and youtubevos when evaluation #33

Closed houhouhouhou11 closed 3 years ago

houhouhouhou11 commented 3 years ago

Hello: Thanks for your reply! I have another question : YouTube-VOS: Download pretrained CFBI, ResNet101-CFBI, to pretrain_models. DAVIS: Download pretrained CFBI, ResNet101-CFBI-DAVIS, to pretrain_models. Does ResNet101-CFBI and ResNet101-CFBI-DAVIS have any difference? Thank you very much!

z-x-yang commented 3 years ago

They are trained on different datasets. No other difference.

leeqiaogithub commented 3 years ago

They are trained on different datasets. No other difference.

resnet101_cfbi.pth is trained on youtubevos,and resnet101_cfbi_davis.pth is obtained by resnet101_cfbi.pth finetune on davisvos. Is that correct?

z-x-yang commented 3 years ago

Right!