# Analysis of Convolutional Neural Networks for Document Image Classification

arXiv: https://arxiv.org/abs/1708.03273 · HTML: https://mlsanity.com/paper/1708.03273/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2017.

## Built on by (most cited first, 13 of 13)

- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [Document AI: Benchmarks, Models and Applications](https://mlsanity.com/paper/2111.08609/) (2021)
- [Evaluating Out-of-Distribution Performance on Document Image Classifiers](https://mlsanity.com/paper/2210.07448/) (2022)
- [VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification](https://mlsanity.com/paper/2205.12029/) (2022)
- [On Evaluation of Document Classification using RVL-CDIP](https://mlsanity.com/paper/2306.12550/) (2023)
- [EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification](https://mlsanity.com/paper/2305.06923/) (2023)
- [DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification](https://mlsanity.com/paper/2407.03830/) (2024)
- [Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents](https://mlsanity.com/paper/2210.05613/) (2022)
- [Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models](https://mlsanity.com/paper/2412.13859/) (2024)
- [End-to-End Document Classification and Key Information Extraction using Assignment Optimization](https://mlsanity.com/paper/2306.00750/) (2023)
- [DWT-CompCNN: Deep Image Classification Network for High Throughput JPEG 2000 Compressed Documents](https://mlsanity.com/paper/2306.01359/) (2023)
- [CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification](https://mlsanity.com/paper/2405.03660/) (2024)
- [An Intelligent Hybrid Model for Identity Document Classification](https://mlsanity.com/paper/2106.04345/) (2021)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) are state-of-the-art models for document image classification tasks. However, many of these approaches rely on parameters and architectures designed for classifying natural images, which differ from document images. We question whether this is appropriate and conduct a large empirical study to find what aspects of CNNs most affect performance on document images. Among other results, we exceed the state-of-the-art on the RVL-CDIP dataset by using shear transform data augmentation and an architecture designed for a larger input image. Additionally, we analyze the learned features and find evidence that CNNs trained on RVL-CDIP learn region-specific layout features.