mPLUG-Huge

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

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

Natural Language Processing4 results

Visual Question Answering (VQA)onVQA v2 test-std
other· 2022-05-24
77.02
SOTA
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections arXiv:2205.12005
Visual Question Answering (VQA)onVQA v2 test-std
overall· 2022-05-24
83.62
best: 84.03 (BEiT-3)
SOTA
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections arXiv:2205.12005
Visual Question Answering (VQA)onVQA v2 test-std
yes/no· 2022-05-24
94.83
best: 94.85 (ONE-PEACE)
SOTA
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections arXiv:2205.12005
Visual Question Answering (VQA)onVQA v2 test-std
number· 2022-05-24
69.82
best: 72.24 (ONE-PEACE)
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections arXiv:2205.12005