Open maoSuxi opened 8 months ago
sry, a little problem, most baseline methods in table 1 use RN50 or ViT as backbone, i think it's better to report the performance on RN50 or ViT to avoid the extra benefit that pre-trained large models brings?
sry, a little problem, most baseline methods in table 1 use RN50 or ViT as backbone, i think it's better to report the performance on RN50 or ViT to avoid the extra benefit that pre-trained large models brings?