AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

DocFormer: End-to-End Transformer for Document Understanding

Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, R. Manmatha

ICCV 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Layout-aware document understanding · 410 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
share spatial embeddings across vision and text (ablation)DocFormer · FUNSDF1: 76.9 vs 75.58 (-1.32 without sharing)Improved
share spatial embeddings across vision and text (ablation)DocFormer · CORDF1: 93.36 vs 92.51 (-0.85 without sharing)Improved
add unsupervised pre-training before fine-tuning (ablation)DocFormer-base · FUNSDF1: 4.18 -> 83.34Improved
add unsupervised pre-training before fine-tuning (ablation)DocFormer-base · CORDF1: 0.54 -> 96.33Improved
add unsupervised pre-training before fine-tuning (ablation)DocFormer-base · RVL-CDIPaccuracy: 93.95 -> 96.17Improved
use a deeper projection head instead of linear (ablation)DocFormer-base · FUNSD (149 train samples)F1: 83.34 -> 82.93 (-0.41)Hurt
use a deeper projection head instead of linear (ablation)DocFormer-base · CORD (800 train samples)F1: 96.33 -> 96.87 (+0.54)Improved
use a deeper projection head instead of linear (ablation)DocFormer-base · RVL-CDIPaccuracy: 96.17 -> 96.85 (+0.68)Improved
add multi-modal MLM to MLM pre-training (ablation)DocFormer · FUNSD (1M-doc pretraining)F1: 72.40 -> 73.91 (+1.51)Improved
add Learn to Reconstruct pre-training task (ablation)DocFormer · FUNSD (1M-doc pretraining)F1: 73.91 -> 74.68 (+0.77)Improved
add Learn to Reconstruct pre-training task (ablation)DocFormer · CORD (1M-doc pretraining)F1: 90.98 -> 92.61 (+1.63)Improved
add Text describes Image pre-training task (ablation)DocFormer · FUNSD (1M-doc pretraining)F1: 74.68 -> 76.90 (+2.23)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy