LXMERT (Pre-train + scratch)

Reported on 3 benchmarks across 2 tasks · 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)onGQA test-dev
Accuracy· 2019-08-20
60
best: 72.1 (CFR)
LXMERT: Learning Cross-Modality Encoder Representations from Transformers arXiv:1908.07490
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2019-08-20
69.9
best: 84.3 (PaLI)
LXMERT: Learning Cross-Modality Encoder Representations from Transformers arXiv:1908.07490

Reasoning1 result

Visual ReasoningonNLVR2 Dev
Accuracy· 2019-08-20
74.9
best: 91.51 (BEiT-3)
SOTA
LXMERT: Learning Cross-Modality Encoder Representations from Transformers arXiv:1908.07490