mlsanityData to 7 Oct 2026

DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis

arXiv 2201.08295 ↗First posted 20 Jan 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning methods have shown strong performance in solving tasks for historical document image analysis. However, despite current libraries and frameworks, programming an experiment or a set of experiments and executing them can be time-consuming. This is why we propose an open-source deep learning framework, DIVA-DAF, which is based on PyTorch Lightning and specifically designed for historical document analysis. Pre-implemented tasks such as segmentation and classification can be easily used or customized. It is also easy to create one's own tasks with the benefit of powerful modules for loading data, even large data sets, and different forms of ground truth. The applications conducted have demonstrated time savings for the programming of a document analysis task, as well as for different scenarios such as pre-training or changing the architecture. Thanks to its data module, the framework also allows to reduce the time of model training significantly.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 52 references that are in the map. First posted on arXiv 20 Jan 2022.

Builds on

23 of 52 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  6. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  7. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  8. 2014OpenML: networked science in machine learningcited by 523
  9. 2021LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysiscited by 58
  10. 2020A Framework For Contrastive Self-Supervised Learning And Designing A New Approachcited by 51
  11. 2019Chainer: A Deep Learning Framework for Accelerating the Research Cyclecited by 22
  12. 2019A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysiscited by 11
11 more
  1. 2019Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscriptscited by 8
  2. 2019Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Networkcited by 6
  3. 2017Open Evaluation Tool for Layout Analysis of Document Imagescited by 5
  4. 2020Self-Supervised Representation Learning on Document Imagescited by 5
  5. 2021Generating Synthetic Handwritten Historical Documents With OCR Constrained GANscited by 5
  6. 2017DocEmul: a Toolkit to Generate Structured Historical Documentscited by 4
  7. 2017A Pitfall of Unsupervised Pre-Trainingcited by 3
  8. 2018DeepDIVA: A Highly-Functional Python Framework for Reproducible Experimentscited by 3
  9. 2014Machine Learning at Scalecited by 2
  10. 2019Improving Reproducible Deep Learning Workflows with DeepDIVAcited by 1
  11. 2021DeepZensols: Deep Natural Language Processing Frameworkcited by 1

Built on by

Not cited yet.