Publications Conference · 2024
Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting
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}
}