mlsanityData to 7 Oct 2026

Analysis of Convolutional Neural Networks for Document Image Classification

arXiv 1708.03273 ↗First posted 10 Aug 2017cs.CVcited by 13

Not on the map. Why?

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.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 3; 2023: 4; 2024: 3.

13 papers.

Sort:

  1. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  2. 2021Document AI: Benchmarks, Models and Applicationscited by 61
  3. 2022Evaluating Out-of-Distribution Performance on Document Image Classifierscited by 16
  4. 2022VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classificationcited by 14
  5. 2023On Evaluation of Document Classification using RVL-CDIPcited by 5
  6. 2023EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classificationcited by 4
  7. 2024DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classificationcited by 4
  8. 2022Contrastive Training Improves Zero-Shot Classification of Semi-structured Documentscited by 3
  9. 2024Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Modelscited by 3
  10. 2023End-to-End Document Classification and Key Information Extraction using Assignment Optimizationcited by 1
  11. 2023DWT-CompCNN: Deep Image Classification Network for High Throughput JPEG 2000 Compressed Documentscited by 1
  12. 2024CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classificationcited by 1
1 more
  1. 2021An Intelligent Hybrid Model for Identity Document Classificationcited by 0