The initial parameters of the model for intra-domain adaptation

feipanir / IntraDA

Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision (CVPR 2020 Oral)

https://arxiv.org/pdf/2004.07703.pdf

MIT License

270 stars 35 forks source link

The initial parameters of the model for intra-domain adaptation #8

Closed weiliuxm closed 4 years ago

weiliuxm commented 4 years ago

Hello, thank you for sharing your codes.

could you tell me the initial parameters of the model in step 3, please? Are they loaded from DeepLab_resnet_pretrained_imagenet.pth or retrained by ADVENT? Thank you in advance.

feipanir commented 4 years ago

Hi we tried both methods of loading from DeepLab_resnet_pretrained_imagenet.pth and also from ADVNET. In our experiments, Deeplab pretrained parameters gives slightly better performance.