search

w1oves / Rein

[CVPR 2024] Official implement of <Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation>
https://zxwei.site/rein
GNU General Public License v3.0
277 stars 22 forks source link

About Table 4 #73

Open IronmanVsThanos opened 1 month ago

IronmanVsThanos commented 1 month ago

Dear Author,

Thank you for your excellent work. Regarding Table 4, you demonstrated the results of Rein's generalization to Cityscapes (Citys) + BDD100K (BDD) + Mapillary (Map) after training on GTAV. To my knowledge, the categories in Mapillary (Map) differ from the other three datasets. In this case, did you perform category mapping during testing? Or how should this be handled? Is there any relevant code available?

Thank you again for your outstanding work.

w1oves commented 1 month ago 
# convert mapillary to cityscape format and resize it for efficient validation
python tools/convert_datasets/mapillary2cityscape.py data/mapillary \
data/mapillary/cityscapes_trainIdLabel --train_id # convert the format
python tools/convert_datasets/mapillary_resize.py data/mapillary/validation/images \
data/mapillary/cityscapes_trainIdLabel/val/label data/mapillary/half/val_img \
data/mapillary/half/val_label # resize the validation data