Scene Text Recognition on CUTE80

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	CPPD	99.7	Yes	Context Perception Parallel Decoder for Scene Te...	2023-07-23	Code
2	CLIP4STR-L (DataComp-1B)	99.7	Yes	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
3	CLIP4STR-B*	99.65	Yes	An Empirical Study of Scaling Law for OCR	2023-12-29	Code
4	MGP-STR	99.31	Yes	Multi-Granularity Prediction for Scene Text Reco...	2022-09-08	Code
5	CLIP4STR-B	99.3	Yes	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
6	DTrOCR 105M	99.1	No	DTrOCR: Decoder-only Transformer for Optical Cha...	2023-08-30	Code
7	CLIP4STR-L	99	Yes	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
8	CCD-ViT-Small(ARD_2.8M)	98.3	Yes	Self-supervised Character-to-Character Distillat...	2022-11-01	Code
9	CCD-ViT-Base(ARD_2.8M)	98.3	Yes	Self-supervised Character-to-Character Distillat...	2022-11-01	Code
10	CCD-ViT-Tiny(ARD_2.8M)	95.8	Yes	Self-supervised Character-to-Character Distillat...	2022-11-01	Code
11	S-GTR	94.7	Yes	Visual Semantics Allow for Textual Reasoning Bet...	2021-12-24	Code
12	MATRN	93.5	No	Multi-modal Text Recognition Networks: Interacti...	2021-11-30	Code
13	SIGA_T	93.1	No	Self-supervised Implicit Glyph Attention for Tex...	2022-03-07	Code
14	DiffusionSTR	92.5	No	DiffusionSTR: Diffusion Model for Scene Text Rec...	2023-06-29	-
15	NRTR+TPS++	92.4	No	TPS++: Attention-Enhanced Thin-Plate Spline for ...	2023-05-09	Code
16	DPAN	91.9	No	-	-	Code
17	CDistNet (Ours)	89.58	No	CDistNet: Perceiving Multi-Domain Character Dist...	2021-11-22	Code

#1CPPD
99.7
Accuracy· Extra Data· 2023-07-23
Context Perception Parallel Decoder for Scene Text Recognition Code
#2CLIP4STR-L (DataComp-1B)SOTA
99.7
Accuracy· Extra Data· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#3CLIP4STR-B*
99.65
Accuracy· Extra Data· 2023-12-29
An Empirical Study of Scaling Law for OCR Code
#4MGP-STRSOTA
99.31
Accuracy· Extra Data· 2022-09-08
Multi-Granularity Prediction for Scene Text Recognition Code
#5CLIP4STR-B
99.3
Accuracy· Extra Data· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#6DTrOCR 105M
99.1
Accuracy· 2023-08-30
DTrOCR: Decoder-only Transformer for Optical Character Recognition Code
#7CLIP4STR-L
99
Accuracy· Extra Data· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#8CCD-ViT-Small(ARD_2.8M)
98.3
Accuracy· Extra Data· 2022-11-01
Self-supervised Character-to-Character Distillation for Text Recognition Code
#9CCD-ViT-Base(ARD_2.8M)
98.3
Accuracy· Extra Data· 2022-11-01
Self-supervised Character-to-Character Distillation for Text Recognition Code
#10CCD-ViT-Tiny(ARD_2.8M)
95.8
Accuracy· Extra Data· 2022-11-01
Self-supervised Character-to-Character Distillation for Text Recognition Code
#11S-GTRSOTA
94.7
Accuracy· Extra Data· 2021-12-24
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition Code
#12MATRNSOTA
93.5
Accuracy· 2021-11-30
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features Code
#13SIGA_T
93.1
Accuracy· 2022-03-07
Self-supervised Implicit Glyph Attention for Text Recognition Code
#14DiffusionSTR
92.5
Accuracy· 2023-06-29
DiffusionSTR: Diffusion Model for Scene Text Recognition
#15NRTR+TPS++
92.4
Accuracy· 2023-05-09
TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition Code
#16DPAN
91.9
Accuracy
No paperCode
#17CDistNet (Ours)SOTA
89.58
Accuracy· 2021-11-22
CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition Code