Multilingual-VQA / sections /limitations.md
gchhablani's picture
Add ToC
b3c9da2
|
raw
history blame
294 Bytes
  • Our best fine-tuned model only achieves 0.49 accuracy on the multilingual validation data that we create. This could be because of not-so-great quality translations, sub-optimal hyperparameters and lack of ample training. In future, we hope to improve this model by addressing such concerns.