Visual Question Answering On Gqa Test Std

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
ProTo	65.14	ProTo: Program-Guided Transformer for Program-Guided Tasks
NSM	63.17	Learning by Abstraction: The Neural State Machine
MDETR-ENB5	62.45	MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
LXMERT	60.3	LXMERT: Learning Cross-Modality Encoder Representations from Transformers
single-hop + LCGN (ours)	56.1	Language-Conditioned Graph Networks for Relational Reasoning
MAC	54.06	GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering
CNN+LSTM	46.55	GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering

0 of 7 row(s) selected.