You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, thanks for open source your nice work! Did you explore other encoder backbones? For example, resnet50. I used resnet50 as encoder but got worse mIOU, specifically 40.7%. How do you think of this?
The text was updated successfully, but these errors were encountered:
Hi @lailvlong , I tried resnet50 before, and as far as I can remember, the performance is slightly better (~1%). According to some recent papers I read, the performance gap between vgg16 and resnet50/101 should be larger. Maybe it requires more careful tuning.
Regarding your results, changing backbone to resnet50 should not cause much performance degradation. Did you use an ImageNet-pretrained resnet50? Or you may try tuning some hyper-parameters (e.g. learning rate, training epochs)
Hello, thanks for open source your nice work! Did you explore other encoder backbones? For example, resnet50. I used resnet50 as encoder but got worse mIOU, specifically 40.7%. How do you think of this?
The text was updated successfully, but these errors were encountered: