ERNIE-ViL-single model

Reported on 4 benchmarks across 1 task · 1 paper

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
number· 2020-06-30
56.79
best: 72.24 (ONE-PEACE)
ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph arXiv:2006.16934
Visual Question Answering (VQA)onVQA v2 test-std
other· 2020-06-30
65.24
best: 77.02 (mPLUG-Huge)
ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph arXiv:2006.16934
Visual Question Answering (VQA)onVQA v2 test-std
overall· 2020-06-30
74.93
best: 84.03 (BEiT-3)
ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph arXiv:2006.16934
Visual Question Answering (VQA)onVQA v2 test-std
yes/no· 2020-06-30
90.83
best: 94.85 (ONE-PEACE)
ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph arXiv:2006.16934