# A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis

arXiv: https://arxiv.org/abs/1905.09113 · HTML: https://mlsanity.com/paper/1905.09113/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2019.

## Built on by (most cited first, 11 of 11)

- [LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis](https://mlsanity.com/paper/2103.15348/) (2021)
- [Generating Synthetic Handwritten Historical Documents With OCR Constrained GANs](https://mlsanity.com/paper/2103.08236/) (2021)
- [dlordinal: a Python package for deep ordinal classification](https://mlsanity.com/paper/2407.17163/) (2024)
- [Efficient few-shot learning for pixel-precise handwritten document layout analysis](https://mlsanity.com/paper/2210.15570/) (2022)
- [Automated Cleanup of the ImageNet Dataset by Model Consensus, Explainability and Confident Learning](https://mlsanity.com/paper/2103.16324/) (2021)
- [Handwriting Recognition with Novelty](https://mlsanity.com/paper/2105.06582/) (2021)
- [Evaluation of a Region Proposal Architecture for Multi-task Document Layout Analysis](https://mlsanity.com/paper/2106.11797/) (2021)
- [Cross-Domain Document Layout Analysis Using Document Style Guide](https://mlsanity.com/paper/2201.09407/) (2022)
- [DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis](https://mlsanity.com/paper/2201.08295/) (2022)
- [A Generic Image Retrieval Method for Date Estimation of Historical Document Collections](https://mlsanity.com/paper/2204.04028/) (2022)
- [Cross-codex Learning for Reliable Scribe Identification in Medieval Manuscripts](https://mlsanity.com/paper/2312.04296/) (2023)

## Abstract (arXiv)

Automatic analysis of scanned historical documents comprises a wide range of image analysis tasks, which are often challenging for machine learning due to a lack of human-annotated learning samples. With the advent of deep neural networks, a promising way to cope with the lack of training data is to pre-train models on images from a different domain and then fine-tune them on historical documents. In the current research, a typical example of such cross-domain transfer learning is the use of neural networks that have been pre-trained on the ImageNet database for object recognition. It remains a mostly open question whether or not this pre-training helps to analyse historical documents, which have fundamentally different image properties when compared with ImageNet. In this paper, we present a comprehensive empirical survey on the effect of ImageNet pre-training for diverse historical document analysis tasks, including character recognition, style classification, manuscript dating, semantic segmentation, and content-based retrieval. While we obtain mixed results for semantic segmentation at pixel-level, we observe a clear trend across different network architectures that ImageNet pre-training has a positive effect on classification as well as content-based retrieval.