Which pre-trained segmentation algorithm is used to get semantic and instance maps?
Btw, as you mentioned in another paper (pix2pixHD), should the instance maps be their boundary map format? However, the instance maps you provided in 'train_inst' folder are just instance maps with cars labeled.
Thank you!
Which pre-trained segmentation algorithm is used to get semantic and instance maps? Btw, as you mentioned in another paper (pix2pixHD), should the instance maps be their boundary map format? However, the instance maps you provided in 'train_inst' folder are just instance maps with cars labeled. Thank you!