Codesota · Models · DoPTA-HR (512×512)1 results · 1 benchmarks
Model card
DoPTA-HR (512×512).
imageTransformer
DoPTA: Improving Document Layout Analysis using Patch-Text Alignment. High-resolution 512×512 variant. Patch-text alignment pretraining. arxiv:2412.12902.
§ 01 · Benchmarks
Every benchmark DoPTA-HR (512×512) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | rvl-cdip | Computer Vision · Document Image Classification | accuracy | 94.1% | #17 | — | 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.
§ 02 · Strengths by area
Where DoPTA-HR (512×512) actually performs.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.