Codesota · Computer Vision · Scene Text Recognition · cute80Tasks/Computer Vision/Scene Text Recognition
Scene Text Recognition · benchmark dataset · 2020 · EN

cute80.

Dataset from Papers With Code

Submit a result ↵
§ 01 · Leaderboard

Best published scores.

20 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary
accuracy · higher is better
accuracy· primary
20 rows
#ModelOrgSubmittedPaper / codeaccuracy
01CPPD—Jul 2023Context Perception Parallel Decoder for Scene Text Recog… · code99.70
02CLIP4STR-L (DataComp-1B)—May 2023CLIP4STR: A Simple Baseline for Scene Text Recognition w… · code99.70
03MGP-STR—Sep 2022Multi-Granularity Prediction for Scene Text Recognition · code99.31
04CLIP4STR-BResearchMay 2023CLIP4STR: A Simple Baseline for Scene Text Recognition w… · code99.30
05DTrOCR 105M—Aug 2023DTrOCR: Decoder-only Transformer for Optical Character R… · code99.10
06CLIP4STR-L—May 2023CLIP4STR: A Simple Baseline for Scene Text Recognition w… · code99
07PARSeqOSSResearchJul 2022Scene Text Recognition with Permuted Autoregressive Sequ…98.61
08CCD-ViT-Small(ARD_2.8M)—Nov 2022Self-supervised Character-to-Character Distillation for … · code98.30
09CCD-ViT-Base(ARD_2.8M)—Nov 2022Self-supervised Character-to-Character Distillation for … · code98.30
10CCD-ViT-Tiny(ARD_2.8M)—Nov 2022Self-supervised Character-to-Character Distillation for … · code95.80
11S-GTR—Dec 2021Visual Semantics Allow for Textual Reasoning Better in S… · code94.70
12MATRNResearchNov 2021Multi-modal Text Recognition Networks: Interactive Enhan… · code93.50
13SIGA_T—Mar 2022Self-supervised Implicit Glyph Attention for Text Recogn… · code93.10
14DiffusionSTR—Jun 2023DiffusionSTR: Diffusion Model for Scene Text Recognition92.50
15NRTR+TPS++—May 2023TPS++: Attention-Enhanced Thin-Plate Spline for Scene Te… · code92.40
16DPAN—Aug 2021papers-with-code · code91.90
17CDistNet (Ours)—Nov 2021CDistNet: Perceiving Multi-Domain Character Distance for… · code89.58
18ABINet-LVOSSFang et al.Mar 2021Read Like Humans: Autonomous, Bidirectional and Iterativ…89.20
19TrOCR-large 558M—Sep 2021TrOCR: Transformer-based Optical Character Recognition w…84.10
20TrOCR-base 334M—Sep 2021TrOCR: Transformer-based Optical Character Recognition w…81.20
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 03 · Progress

7 steps
of state of the art.

Each row below marks a model that broke the previous record on accuracy. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · accuracy
  1. Mar 6, 2021ABINet-LVFang et al.89.20
  2. Aug 1, 2021DPAN91.90
  3. Nov 30, 2021MATRNResearch93.50
  4. Dec 24, 2021S-GTR94.70
  5. Jul 14, 2022PARSeqResearch98.61
  6. Sep 8, 2022MGP-STR99.31
  7. May 23, 2023CLIP4STR-L (DataComp-1B)99.70
Fig 3 · SOTA-setting models only. 7 entries span Mar 2021 → May 2023.
§ 04 · Literature

14 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies
cute80 — Scene Text Recognition benchmark · Codesota | CodeSOTA