Publications Conference · 2024

Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting

O. Hamed, S. Bakkali, M. B. Blaschko, M.-F. Moens, J. Van Landeghem

Document Analysis and Recognition – ICDAR 2024 (LNCS), pp. 270–286

In one paragraph

The first multimodal early-exit design for visually rich document understanding: training strategies, exit types and placements that reach a Pareto-optimal trade-off, cutting latency by over 20% while fully retaining baseline accuracy.

Cite

@inproceedings{hamed2024multimodal,
  title     = {{Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting}},
  author    = {Hamed, Omar and Bakkali, Souhail and Blaschko, Matthew B. and Moens, Marie-Francine and Van Landeghem, Jordy},
  booktitle = {Document Analysis and Recognition – ICDAR 2024},
  pages     = {270--286},
  year      = {2024},
  doi       = {10.1007/978-3-031-70546-5_16},
  url       = {https://arxiv.org/abs/2405.12705}
}