# Domain Agnostic Few-Shot Learning For Document Intelligence

arXiv: https://arxiv.org/abs/2111.00007 · HTML: https://mlsanity.com/paper/2111.00007/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Builds on (most cited first, 22 of 22)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [A Survey of Deep Meta-Learning](https://mlsanity.com/paper/2010.03522/) (2020)
- [Dense Classification and Implanting for Few-Shot Learning](https://mlsanity.com/paper/1903.05050/) (2019)
- [Self-Supervised Learning For Few-Shot Image Classification](https://mlsanity.com/paper/1911.06045/) (2019)
- [Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification](https://mlsanity.com/paper/2005.08463/) (2020)
- [Cross-Domain Few-Shot Learning with Meta Fine-Tuning](https://mlsanity.com/paper/2005.10544/) (2020)
- [Self-Net: Lifelong Learning via Continual Self-Modeling](https://mlsanity.com/paper/1805.10354/) (2018)
- [Continual Learning with Deep Artificial Neurons](https://mlsanity.com/paper/2011.07035/) (2020)
- [Deep Active Learning via Open Set Recognition](https://mlsanity.com/paper/2007.02196/) (2020)
- [A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2006.11384/) (2020)
- [Efficient Document Image Classification Using Region-Based Graph Neural Network](https://mlsanity.com/paper/2106.13802/) (2021)

## Built on by (most cited first, 1 of 1)

- [Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation](https://mlsanity.com/paper/2305.14828/) (2023)

## Abstract (arXiv)

Few-shot learning aims to generalize to novel classes with only a few samples with class labels. Research in few-shot learning has borrowed techniques from transfer learning, metric learning, meta-learning, and Bayesian methods. These methods also aim to train models from limited training samples, and while encouraging performance has been achieved, they often fail to generalize to novel domains. Many of the existing meta-learning methods rely on training data for which the base classes are sampled from the same domain as the novel classes used for meta-testing. However, in many applications in the industry, such as document classification, collecting large samples of data for meta-learning is infeasible or impossible. While research in the field of the cross-domain few-shot learning exists, it is mostly limited to computer vision. To our knowledge, no work yet exists that examines the use of few-shot learning for classification of semi-structured documents (scans of paper documents) generated as part of a business workflow (forms, letters, bills, etc.). Here the domain shift is significant, going from natural images to the semi-structured documents of interest. In this work, we address the problem of few-shot document image classification under domain shift. We evaluate our work by extensive comparisons with existing methods. Experimental results demonstrate that the proposed method shows consistent improvements on the few-shot classification performance under domain shift.