Document Image Classification On Rvl Cdip

评估指标

Accuracy

Parameters

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
EAML	97.70%	-	EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification	-
Cross-Modal	97.05%	197M	Visual and Textual Deep Feature Fusion for Document Image Classification	-
DocFormerBASE	96.17%	183M	DocFormer: End-to-End Transformer for Document Understanding
LayoutLMV3Large	95.93%	368M	LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
LiLT[EN-R]BASE	95.68%	-	LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
LayoutLMv2LARGE	95.64%	-	LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
TILT-Large	95.52%	-	Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer
DocFormer large	95.50%	536M	DocFormer: End-to-End Transformer for Document Understanding
LayoutLMv3BASE	95.44%	133M	LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
Donut	95.3%	-	OCR-free Document Understanding Transformer
TILT-Base	95.25%	-	Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer
LayoutLMv2BASE	95.25%	200M	LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
LayoutXLM	95.21%	-	LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
StrucTexTv2 (large)	94.62%	238M	StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
Pre-trained LayoutLM	94.42%	160M	LayoutLM: Pre-training of Text and Layout for Document Image Understanding
DoPTA	94.12%	85M	DoPTA: Improving Document Layout Analysis using Patch-Text Alignment	-
DocXClassifier-B	94.00%	95.4M	DocXClassifier: High Performance Explainable Deep Network for Document Image Classification	-
StrucTexTv2 (small)	93.4%	28M	StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
VLCDoC	93.19%	217M	VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification	-
TransferDoc	93.18%	221M	GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification	-

0 of 31 row(s) selected.