Hello, in table 3 you compare ViCHa with ALBEF (1.1M), the label of this table: "Zero-shot Comparison with SOTA on Flickr30K (after fine-tuning ViCHA on COCO) and COCO (pretrained model only)". Was ALBEF fine-tuned on COCO before evaluation on Flickr30K too?
Hello, in table 3 you compare ViCHa with ALBEF (1.1M), the label of this table: "Zero-shot Comparison with SOTA on Flickr30K (after fine-tuning ViCHA on COCO) and COCO (pretrained model only)". Was ALBEF fine-tuned on COCO before evaluation on Flickr30K too?