Hi-VT5 base fine-tuned on MP-DocVQA

This is Hierarchical Visual T5 (Hi-VT5) base fine-tuned on Multipage DocVQA (MP-DocVQA) dataset.

This model was proposed in Hierarchical multimodal transformers for Multi-Page DocVQA.

• Results on the MP-DocVQA dataset are reported in Table 2.
• Training hyperparameters can be found in Table 8 of Appendix D.

Disclaimer: Due to some issues, this model does not achieve as good results as the reported ones in the paper. Please refer to the project Github for more details.

How to use

Hi-VT5 is not integrated into HF yet. Please download the code from Github repository and follow the instructions.

Metrics

Average Normalized Levenshtein Similarity (ANLS)

The standard metric for text-based VQA tasks (ST-VQA and DocVQA). It evaluates the method's reasoning capabilities while smoothly penalizes OCR recognition errors. Check Scene Text Visual Question Answering for detailed information.

Answer Page Prediction Accuracy (APPA)

In the MP-DocVQA task, the models can provide the index of the page where the information required to answer the question is located. For this subtask accuracy is used to evaluate the predictions: i.e. if the predicted page is correct or not. Check Hierarchical multimodal transformers for Multi-Page DocVQA for detailed information.

Model results

Extended experimentation can be found in Table 2 of Hierarchical multimodal transformers for Multi-Page DocVQA. You can also check the live leaderboard at the RRC Portal.

Citation Information

@article{tito2022hierarchical,
  title={Hierarchical multimodal transformers for Multi-Page DocVQA},
  author={Tito, Rub{\`e}n and Karatzas, Dimosthenis and Valveny, Ernest},
  journal={arXiv preprint arXiv:2212.05935},
  year={2022}
}