CLIP-Single

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)onVizWiz 2020 VQA
overall· 2022-06-10
60.66
best: 73.3 (PaLI)
Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model arXiv:2206.05281
Visual Question Answering (VQA)onVizWiz 2020 Answerability
average_precision· 2022-06-10
82.86
best: 84.13 (CLIP-Ensemble)
Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model arXiv:2206.05281