Scene Text Recognition On Iiit5K

Metrics

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
DTrOCR 105M	99.6	DTrOCR: Decoder-only Transformer for Optical Character Recognition
CLIP4STR-L (DataComp-1B)	99.6	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CLIP4STR-B (DataComp-1B)	99.5	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CLIP4STR-L	99.5	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CPPD	99.3	Context Perception Parallel Decoder for Scene Text Recognition
CLIP4STR-B	99.2	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
PARSeq	99.1±0.1	Scene Text Recognition with Permuted Autoregressive Sequence Models
MGP-STR	98.8	Multi-Granularity Prediction for Scene Text Recognition
CCD-ViT-Small(ARD_2.8M)	98.0	Self-supervised Character-to-Character Distillation for Text Recognition
CCD-ViT-Base(ARD_2.8M)	98.0	Self-supervised Character-to-Character Distillation for Text Recognition
S-GTR	97.5	Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
DiffusionSTR	97.3	DiffusionSTR: Diffusion Model for Scene Text Recognition
CCD-ViT-Tiny(ARD_2.8M)	97.1	Self-supervised Character-to-Character Distillation for Text Recognition
SIGA_S	96.9	Self-supervised Implicit Glyph Attention for Text Recognition
MATRN	96.6	Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
CDistNet (Ours)	96.57	CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
DPAN	96.2	Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition

0 of 17 row(s) selected.