2D Semantic Segmentation on ICDAR2013

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	CLIP4STR-L*	99.42	Yes	An Empirical Study of Scaling Law for OCR	2023-12-29	Code
2	DTrOCR 105M	99.4	No	DTrOCR: Decoder-only Transformer for Optical Cha...	2023-08-30	Code
3	CLIP4STR-L (DataComp-1B)	99	No	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
4	MGP-STR	98.5	Yes	Multi-Granularity Prediction for Scene Text Reco...	2022-09-08	Code
5	CLIP4STR-L	98.5	Yes	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
6	CCD-ViT-Base(ARD_2.8M)	98.3	Yes	Self-supervised Character-to-Character Distillat...	2022-11-01	Code
7	CCD-ViT-Small(ARD_2.8M)	98.3	Yes	Self-supervised Character-to-Character Distillat...	2022-11-01	Code
8	CLIP4STR-B	98.3	Yes	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
9	MATRN	97.9	No	Multi-modal Text Recognition Networks: Interacti...	2021-11-30	Code
10	S-GTR	97.8	Yes	Visual Semantics Allow for Textual Reasoning Bet...	2021-12-24	Code
11	SIGA_T	97.8	No	Self-supervised Implicit Glyph Attention for Tex...	2022-03-07	Code
12	DPAN	97.7	No	-	-	Code
13	CDistNet (Ours)	97.67	No	CDistNet: Perceiving Multi-Domain Character Dist...	2021-11-22	Code
14	CCD-ViT-Tiny(ARD_2.8M)	97.5	Yes	Self-supervised Character-to-Character Distillat...	2022-11-01	Code
15	SVTR-L (Large)	97.2	No	SVTR: Scene Text Recognition with a Single Visua...	2022-04-30	Code
16	SVTR-B (Base)	97.1	No	SVTR: Scene Text Recognition with a Single Visua...	2022-04-30	Code
17	DiffusionSTR	97.1	No	DiffusionSTR: Diffusion Model for Scene Text Rec...	2023-06-29	-
18	Yet Another Text Recognizer	96.8	No	Why You Should Try the Real Data for the Scene T...	2021-07-29	Code
19	SVTR-T (Tiny)	96.3	No	SVTR: Scene Text Recognition with a Single Visua...	2022-04-30	Code
20	SVTR-S (Small)	95.7	No	SVTR: Scene Text Recognition with a Single Visua...	2022-04-30	Code
21	SRN	95.5	No	Towards Accurate Scene Text Recognition with Sem...	2020-03-27	Code
22	RCEED	94.7	No	Representation and Correlation Enhanced Encoder-...	2021-06-13	Code
23	SATRN	94.1	No	On Recognizing Texts of Arbitrary Shapes with 2D...	2019-10-10	Code
24	DAN	93.9	No	Decoupled Attention Network for Text Recognition	2019-12-21	Code
25	CSTR	93.2	No	Revisiting Classification Perspective on Scene T...	2021-02-22	Code
26	TextScanner	92.9	No	TextScanner: Reading Characters in Order for Rob...	2019-12-28	-
27	SEED	92.8	No	SEED: Semantics Enhanced Encoder-Decoder Framewo...	2020-05-22	Code
28	SAFL	92.8	No	SAFL: A Self-Attention Scene Text Recognizer wit...	2022-01-01	Code
29	ViTSTR	92.4	No	Vision Transformer for Fast and Efficient Scene ...	2021-05-18	Code
30	Baek et al.	92.3	No	What Is Wrong With Scene Text Recognition Model ...	2019-04-03	Code
31	ASTER	91.8	No	-	-	Code
32	CA-FCN	91.5	No	Scene Text Recognition from Two-Dimensional Pers...	2018-09-18	-
33	SAR	91	No	Show, Attend and Read: A Simple and Strong Basel...	2018-11-02	Code
34	STAR-Net	89.1	No	-	-	Code
35	RARE	88.6	No	Robust Scene Text Recognition with Automatic Rec...	2016-03-12	Code
36	CRNN	86.7	No	An End-to-End Trainable Neural Network for Image...	2015-07-21	Code
37	CHAR	79.5	No	Synthetic Data and Artificial Neural Networks fo...	2014-06-09	Code

#1CLIP4STR-L*SOTA
99.42
Accuracy· Extra Data· 2023-12-29
An Empirical Study of Scaling Law for OCR Code
#2DTrOCR 105MSOTA
99.4
Accuracy· 2023-08-30
DTrOCR: Decoder-only Transformer for Optical Character Recognition Code
#3CLIP4STR-L (DataComp-1B)SOTA
99
Accuracy· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#4MGP-STRSOTA
98.5
Accuracy· Extra Data· 2022-09-08
Multi-Granularity Prediction for Scene Text Recognition Code
#5CLIP4STR-L
98.5
Accuracy· Extra Data· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#6CCD-ViT-Base(ARD_2.8M)
98.3
Accuracy· Extra Data· 2022-11-01
Self-supervised Character-to-Character Distillation for Text Recognition Code
#7CCD-ViT-Small(ARD_2.8M)
98.3
Accuracy· Extra Data· 2022-11-01
Self-supervised Character-to-Character Distillation for Text Recognition Code
#8CLIP4STR-B
98.3
Accuracy· Extra Data· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#9MATRNSOTA
97.9
Accuracy· 2021-11-30
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features Code
#10S-GTR
97.8
Accuracy· Extra Data· 2021-12-24
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition Code
#11SIGA_T
97.8
Accuracy· 2022-03-07
Self-supervised Implicit Glyph Attention for Text Recognition Code
#12DPAN
97.7
Accuracy
No paperCode
#13CDistNet (Ours)SOTA
97.67
Accuracy· 2021-11-22
CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition Code
#14CCD-ViT-Tiny(ARD_2.8M)
97.5
Accuracy· Extra Data· 2022-11-01
Self-supervised Character-to-Character Distillation for Text Recognition Code
#15SVTR-L (Large)
97.2
Accuracy· 2022-04-30
SVTR: Scene Text Recognition with a Single Visual Model Code
#16SVTR-B (Base)
97.1
Accuracy· 2022-04-30
SVTR: Scene Text Recognition with a Single Visual Model Code
#17DiffusionSTR
97.1
Accuracy· 2023-06-29
DiffusionSTR: Diffusion Model for Scene Text Recognition
#18Yet Another Text RecognizerSOTA
96.8
Accuracy· 2021-07-29
Why You Should Try the Real Data for the Scene Text Recognition Code
#19SVTR-T (Tiny)
96.3
Accuracy· 2022-04-30
SVTR: Scene Text Recognition with a Single Visual Model Code
#20SVTR-S (Small)
95.7
Accuracy· 2022-04-30
SVTR: Scene Text Recognition with a Single Visual Model Code
#21SRNSOTA
95.5
Accuracy· 2020-03-27
Towards Accurate Scene Text Recognition with Semantic Reasoning Networks Code
#22RCEED
94.7
Accuracy· 2021-06-13
Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition Code
#23SATRNSOTA
94.1
Accuracy· 2019-10-10
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention Code
#24DAN
93.9
Accuracy· 2019-12-21
Decoupled Attention Network for Text Recognition Code
#25CSTR
93.2
Accuracy· 2021-02-22
Revisiting Classification Perspective on Scene Text Recognition Code
#26TextScanner
92.9
Accuracy· 2019-12-28
TextScanner: Reading Characters in Order for Robust Scene Text Recognition
#27SEED
92.8
Accuracy· 2020-05-22
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition Code
#28SAFL
92.8
Accuracy· 2022-01-01
SAFL: A Self-Attention Scene Text Recognizer with Focal Loss Code
#29ViTSTR
92.4
Accuracy· 2021-05-18
Vision Transformer for Fast and Efficient Scene Text Recognition Code
#30Baek et al.SOTA
92.3
Accuracy· 2019-04-03
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis Code
#31ASTER
91.8
Accuracy
No paperCode
#32CA-FCNSOTA
91.5
Accuracy· 2018-09-18
Scene Text Recognition from Two-Dimensional Perspective
#33SAR
91
Accuracy· 2018-11-02
Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition Code
#34STAR-Net
89.1
Accuracy
No paperCode
#35RARESOTA
88.6
Accuracy· 2016-03-12
Robust Scene Text Recognition with Automatic Rectification Code
#36CRNNSOTA
86.7
Accuracy· 2015-07-21
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition Code
#37CHARSOTA
79.5
Accuracy· 2014-06-09
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition Code