Model card
DAN.
UnknownunknownUnknown paramsUnknown2 current SOTA
Imported from Papers With Code
§ 02 · Benchmarks
Every benchmark DAN has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | simara | Computer Vision · Optical Character Recognition | cer | 6.5% | #1 | 2023-04-26 | source ↗ |
| 02 | simara | Computer Vision · Optical Character Recognition | wer | 14.8% | #1 | 2023-04-26 | source ↗ |
| 03 | read-2016 | Computer Vision · Optical Character Recognition | wer | 13.6% | #2 | 2022-03-23 | source ↗ |
| 04 | read-2016 | Computer Vision · Optical Character Recognition | cer | 3.2% | #2 | 2022-03-23 | source ↗ |
| 05 | read2016(line-level) | Computer Vision · Optical Character Recognition | test-wer | 17.6% | #2 | 2022-03-23 | source ↗ |
| 06 | read2016(line-level) | Computer Vision · Optical Character Recognition | test-cer | 4.1% | #3 | 2022-03-23 | source ↗ |
| 07 | icdar-2003 | Computer Vision · Scene Text Recognition | accuracy | 95.0% | #4 | 2019-12-21 | source ↗ |
| 08 | icdar2013 | Computer Vision · Optical Character Recognition | accuracy | 93.9% | #23 | 2019-12-21 | source ↗ |
| 09 | icdar2015 | Computer Vision · Optical Character Recognition | accuracy | 74.5% | #25 | 2019-12-21 | source ↗ |
| 10 | svt | Computer Vision · Scene Text Recognition | accuracy | 89.2% | #30 | 2019-12-21 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where DAN actually performs.
§ 04 · Papers
3 papers with results for DAN.
- 2023-04-26· Computer Vision· 2 results
SIMARA: a database for key-value information extraction from full pages
- 2022-03-23· Computer Vision· 4 results
DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition
- 2019-12-21· Computer Vision· 4 results
Decoupled Attention Network for Text Recognition
§ 05 · Related models
Other Unknown models scored on Codesota.
CRAFT
Unknown params · 21 results
GPT-2-Large (fine-tuning)
Unknown params · 20 results
HTLM (fine-tuning)
Unknown params · 20 results
TextFuseNet (ResNeXt-101)
Unknown params · 16 results
MixNet
Unknown params · 13 results
PAN
Unknown params · 12 results
SPCNET
Unknown params · 12 results
TESTR
Unknown params · 12 results
§ 06 · Sources & freshness
Where these numbers come from.
papers-with-code
10
results
10 of 10 rows marked verified. · first result 2019-12-21, latest 2023-04-26.