EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification. (arXiv:2305.06923v1 [cs.CV])

In the recent past, complex deep neural networks have received huge interest
in various document understanding tasks such as document image classification
and document retrieval. As many document types have a distinct visual style,
learning only visual features with deep CNNs to classify document images have
encountered the problem of low inter-class discrimination, and high intra-class
structural variations between its categories. In parallel, text-level
understanding jointly learned with the corresponding visual properties within a
given document image has considerably improved …

arxiv attention classification cnns document understanding ensemble features image images network networks neural networks retrieval self-attention types understanding