Hi all, So, I just created my first LayoutLMv3 model for token classification over the FUNSD dataset. Now, I would like to fine tune it with my own version of FUNSD dataset. But, since the amout of documents is not big enough, data augmentation comes to mind. I need some guidance on this topic. Si…

Hi, No since the text to be extracted will change if you use things like random cropping or flipping. For document AI, one typically applies augmentation like here: https://github.com/facebookresearch/nougat/blob/f5d2cd525979e24c01c72fe223feff2eda555a0c/nougat/transforms.py . Things like erosion, d…

Data augmentation FUNSD dataset & LayoutLMv3

Beginners

aghenghiu October 31, 2023, 12:31pm 2

@nielsr is your answer here aplicable in this specific scenario?

Topic		Replies	Views
Can a Model Learn to Generate Better Augmented Data? 🤗Transformers	0	39	August 20, 2025
LayoutLMv3 paper review and fine tuning code Awesome paper	0	1285	June 23, 2022
Using Huggingface for computer vision (Tensorflow)? 🤗Transformers	3	506	June 2, 2025
Data augmentation for image (ViT) using Hugging Face Beginners	9	6312	December 10, 2021
LayoutLM model annotation regarding Beginners	2	1097	May 3, 2023

Data augmentation FUNSD dataset & LayoutLMv3

Related topics