Questions about Deeplab retrain part

[Unrealluver]

Greetings！

I read your paper again and again recently, and I really learned a lot from your work. For the retrain part, I met some problems, would you like to help to answer?

At first, I noticed that your results in Table.4 were devided into 3 parts, the subtitle of first part is Segmentation Network : DeepLab-Large-FOV (VGG-16), the 2st part is Segmentation Network : DeepLab-Large-FOV (ResNet-101), the 3rd part is Segmentation Network : DeepLab-ASPP (ResNet-101).

My first question is that your deeplab retrained script(/DRS/DeepLab-V2-PyTorch/train.sh) indicate which part in Table.4 we mentioned before? What about other two parts' code? I could not find a VGG-Backboned model in DeepLab-V2-PyTorch folder.

[qjadud1994]

Thank you for your interest in our work.

For your first question, DeepLab Large-FOV is equal to DeepLab-V1, and DeepLab-ASPP is equal to DeepLab-V2. The DeepLab-V2 code produces DeepLab-ASPP (ResNet-101) performance.

Since most of the recent works adopt DeepLab-V2 or V3, which shows higher performance than DeepLab-V1, we upload only the DeepLab-V2 (DeepLab-ASPP) code.

If you need the DeepLab-V1 (DeepLab Large-FOV (VGG-16 or ResNet-101) code, we will upload that soon.

[Unrealluver]

Thank you for your interest in our work.

For your first question, DeepLab Large-FOV is equal to DeepLab-V1, and DeepLab-ASPP is equal to DeepLab-V2. The DeepLab-V2 code produces DeepLab-ASPP (ResNet-101) performance.

Since most of the recent works adopt DeepLab-V2 or V3, which shows higher performance than DeepLab-V1, we upload only the DeepLab-V2 (DeepLab-ASPP) code.

If you need the DeepLab-V1 (DeepLab Large-FOV (VGG-16 or ResNet-101) code, we will upload that soon.

Thank you for your early replay, looking for your additional code!