Multiple Context Learning Networks for Visual Question Answering

Table 5

Comparison with the current state-of-the-art methods on GQA test datasets.

Model	Test-dev	Test
CNN + LSTM [5]	—	46.6
BUTD [13]	—	49.7
MAC [15]	—	54.1
LCGN [19]	55.8	56.1
OCCAM [31]	56.2	56.3
MCLN-LSTM	56.4	56.6
MCLN-BERT	56.8	57.0