Giters

beacandler / EATEN

EATEN: Entity-aware Attention for Single Shot Visual Text Extraction

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why "Use CycleGan or domain adaptation" to synth data to train EATEN?

PirateX0 opened this issue · comments

commented

Thank you for sharing the data. It's very helpful.
In your "todo" list, you mentioned, "Use CycleGan or domain adaptation to synth data to train EATEN."
The current generation results seem impressive, and I'm curious why CycleGan is needed to synthesize images?