StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
| Autor: | Yu, Yuechen, Li, Yulin, Zhang, Chengquan, Zhang, Xiaoqiang, Guo, Zengyuan, Qin, Xiameng, Yao, Kun, Han, Junyu, Ding, Errui, Wang, Jingdong |
|---|---|
| Rok vydání: | 2023 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | In this paper, we present StrucTexTv2, an effective document image pre-training framework, by performing masked visual-textual prediction. It consists of two self-supervised pre-training tasks: masked image modeling and masked language modeling, based on text region-level image masking. The proposed method randomly masks some image regions according to the bounding box coordinates of text words. The objectives of our pre-training tasks are reconstructing the pixels of masked image regions and the corresponding masked tokens simultaneously. Hence the pre-trained encoder can capture more textual semantics in comparison to the masked image modeling that usually predicts the masked image patches. Compared to the masked multi-modal modeling methods for document image understanding that rely on both the image and text modalities, StrucTexTv2 models image-only input and potentially deals with more application scenarios free from OCR pre-processing. Extensive experiments on mainstream benchmarks of document image understanding demonstrate the effectiveness of StrucTexTv2. It achieves competitive or even new state-of-the-art performance in various downstream tasks such as image classification, layout analysis, table structure recognition, document OCR, and information extraction under the end-to-end scenario. Comment: ICLR 2023 |
| Databáze: | arXiv |
| Externí odkaz: |
|