TILT-Large

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Visual Question Answering (VQA)onInfographicVQA
ANLS· uses extra data· 2021-02-18
61.2
best: 80.3 (Gemini Ultra (pixel only))
SOTA
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer arXiv:2102.09550
Visual Question Answering (VQA)onDocVQA test
ANLS· uses extra data· 2021-02-18
0.8705
best: 0.9436 (Human)
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer arXiv:2102.09550