Alignment-enriched tuning for patch-level pre-trained document image models
Alignment between image and text has shown promising im provements on patch-level pre-trained document image mod els. However, investigating more effective or finer-grained alignment techniques during pre-training requires a large amount of computation cost and time. Thus, a question natu rally aris...
Saved in:
Main Authors: | WANG, Lei, HE, Jiabang, XU, Xing, LIU, Ning, LIU, Hui |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9318 https://ink.library.smu.edu.sg/context/sis_research/article/10318/viewcontent/Alignment_Enriched_pv.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction
by: HE, Jiabang, et al.
Published: (2023) -
Mitigating fine-grained hallucination by fine-tuning large vision-language models with caption rewrites
by: WANG, Lei, et al.
Published: (2024) -
NumGPT: Improving numeracy ability of generative pre-trained models
by: JIN, Zhihua, et al.
Published: (2023) -
ROME: Evaluating pre-trained vision-language models on reasoning beyond visual common sense
by: ZHOU, Kankan, et al.
Published: (2023) -
Do-GOOD: Towards distribution shift evaluation for pre-trained visual document understanding models
by: HE, Jiabang, et al.
Published: (2023)