DMN

Reported on 2 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 Processing2 results

Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2018-02-15
68.09
best: 84.3 (PaLI)
Learning to Count Objects in Natural Images for Visual Question Answering arXiv:1802.05766
Visual Question Answering (VQA)onVQA v2 test-std
overall· 2018-02-15
68.4
best: 84.03 (BEiT-3)
Learning to Count Objects in Natural Images for Visual Question Answering arXiv:1802.05766