HybriDLA: Hybrid Generation for Document Layout Analysis
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 3147-3155
DOI: 10.1609/aaai.v40i4.37308 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yufan Chen und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number of regions, this paradigm struggles with contemporary documents, which exhibit diverse element counts and increasingly complex layouts. To address challenges posed by modern documents, we present HybriDLA, a novel generative framework that unifies diffusion and autoregressive decoding within a single layer. The diffusion component iteratively refines bounding-box hypotheses, whereas the autoregressive component injects semantic and contextual awareness, enabling precise region prediction even in highly varied layouts. To further enhance detection quality, we design a multi-scale feature-fusion encoder that captures both fine-grained and high-level visual cues. This architecture elevates performance to 83.5% mean Average Precision (mAP). Extensive experiments on the DocLayNet and M6Doc benchmarks demonstrate that HybriDLA sets a state-of-the-art performance, outperforming previous approaches.
Zitieren
APA
Chen, Y., Moured, O., Liu, R., Zheng, J., Peng, K., Zhang, J., & Stiefelhagen, R. (2026). HybriDLA: Hybrid Generation for Document Layout Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 3147-3155. https://doi.org/10.1609/aaai.v40i4.37308
Vancouver
Chen Y, Moured O, Liu R, Zheng J, Peng K, Zhang J, et al. HybriDLA: Hybrid Generation for Document Layout Analysis. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):3147-3155. doi:10.1609/aaai.v40i4.37308
BibTeX
@article{Chen2026,
author = {Chen, Yufan and Moured, Omar and Liu, Ruiping and Zheng, Junwei and Peng, Kunyu and Zhang, Jiaming and Stiefelhagen, Rainer},
title = {HybriDLA: Hybrid Generation for Document Layout Analysis},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {3147--3155},
doi = {10.1609/aaai.v40i4.37308}
}
EUVIMED