VLKD(ViT-B/16)

Reported on 2 benchmarks across 1 task

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)onOK-VQA
Accuracy
10.5
best: 66.8 (PaLI-X-VPD)
Visual Question Answering (VQA)onVQA v2 val
Accuracy
38.6
best: 82.19 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))