WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language Models
WAON, the largest publicly available native Japanese image-text dataset constructed from native Japanese web content in Common Crawl, is presented and it is observed that models fine-tuned on WAON consistently achieve stronger performance on Japanese cultural benchmarks than those fine-tuned on English-to-Japanese tran...
Issa Sugiura, Shuhei Kurita, Yusuke Oda et al.
· 0 citations