About finetune on f30k.
GuoBruce opened this issue · comments
GuoBruce commented
Hi, I am very interested in your work! I am wondering why use 15 texts as negative samples instead of 1 text during the finetune period. And what do you think training the model from scratch only using flickr30k dataset?
Wonjae Kim commented
Hi @GuoBruce,
We didn't test training filckr30k from scratch but I believe the result would be much worse.
The number 15
is totally arbitrary. (though Pixel-BERT used similar 20
negative samples for IR/TR)
GuoBruce commented
Thanks for your reply! I did a try and found that it is absolutely worse than I hoped. The recall@1 is between 10 and 20.