Codesota · Models · HEADoC-Large2 results · 2 benchmarks
Model card
HEADoC-Large.
multimodal90.58M paramsTransformer
HEADoC: Highly Efficient and Accurate Document Classifier Optimized Using Semantic Distances. LARGE variant. Hybrid deep attention mechanism fusing visual and textual modalities. DOI:10.1007/s13748-025-00411-x.
§ 01 · Benchmarks
Every benchmark HEADoC-Large has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | tobacco-3482 | Computer Vision · Document Image Classification | accuracy | 96.7% | #1 | — | source ↗ |
| 02 | rvl-cdip | Computer Vision · Document Image Classification | accuracy | 93.6% | #19 | — | 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 HEADoC-Large actually performs.
§ 05 · Sources & freshness
Where these numbers come from.
HEADoC: Highly Efficient and Accurate Document Classifier Optimized Using Semantic Distances
1
result
springer
1
result
2 of 2 rows marked verified.