List your company

Visual Question Answering on IrSD-VQA

82AccuracySpatialPIN
52.8860.446875.56Mar 18, 2024

Evaluation results

MethodLinks
SpatialPINBackbone=GPT-4o2024.0382————
GPT-4oBackbone=GPT-4o2024.0364————
SpatialVLMBackbone=PaLM 2-E2024.0354————
GPT-4o2024.03—301042
GPT-4o + SpatialPINBackbone=GPT-4o2024.03—100685438
SpatialVLMBackbone=PaLM 2-E2024.03—7826124