Visual Question Answering On Qlevr

Overall Accuracy

Results

Performance results of various models on this benchmark

Model Name	Overall Accuracy	Paper Title
CNN+LSTM	65.9	QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning
BERT	65.8	QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning
MAC	66.5	QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning
Q-type	50.0	QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning
LSTM	64.6	QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning

0 of 5 row(s) selected.