Efficient Document Image Classification Using Region-Based Graph Neural Network

Open paper
Benchmark Model Rank Results
document-image-classification-on-tobacco-3482BERT [BERT]–Accuracy: 79
document-image-classification-on-tobacco-3482DocBERT [DOCBERT]–Accuracy: 82.3
document-image-classification-on-tobacco-3482DocBert [DOCBERT]–Accuracy: 91.95
document-image-classification-on-tobacco-3482Eff-GNN + Word2Vec [word2vec]–Accuracy: 91
document-image-classification-on-tobacco-3482Eff-GNN + Word2Vec [word2vec] + Image Embedding–Accuracy: 77.5
document-image-classification-on-tobacco-3482Eff-GNN+ Word2Vec [word2vec]–Accuracy: 73.5
document-image-classification-on-tobacco-3482VGG–Memory: 7.08

Rank counts only results with a code link.