semantic-segmentation-pytorch icon indicating copy to clipboard operation
semantic-segmentation-pytorch copied to clipboard

On using non-dilated Resnet weights for dilated Resnets

Open daveboat opened this issue 4 years ago • 0 comments

For the dilated ResNets (resnet50-dilated, resnet101-dilated, etc), the same pretrained weights as the non-dilated ResNets are used. Even though only the last two layers are different (so all earlier layers should be okay in terms of weights), wouldn't we expect significantly degraded performance if we naively use regular ResNet weights, but with an operation which removes striding and adds dilation?

Am I missing something?

daveboat avatar Aug 27 '20 20:08 daveboat