Improving accuracy and speeding up Document Image Classification through parallel systems

16 Jun 2020Javier FerrandoJuan Luis DominguezJordi TorresRaul GarciaDavid GarciaDaniel GarridoJordi CortadaMateo Valero

This paper presents a study showing the benefits of the EfficientNet models compared with heavier Convolutional Neural Networks (CNNs) in the Document Classification task, essential problem in the digitalization process of institutions. We show in the RVL-CDIP dataset that we can improve previous results with a much lighter model and present its transfer learning capabilities on a smaller in-domain dataset such as Tobacco3482... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Document Image Classification RVL-CDIP Pre-trained EfficientNet Accuracy 92.31% # 2
Multi-Modal Document Classification Tobacco-3482 EfficientNet+BERT Accuracy 89.47% # 1

Methods used in the Paper