Visual Question Answering on VQA 1.0 (test-dev) benchmark leaderboard · SOTA2 Research

Visual Question Answering on VQA 1.0 (test-dev)

67.42Overall AccuracyMUTAN

Evaluation Results

Method
MUTAN2017.05	67.42	85.14	39.81	58.52
MUTAN2017.05	67.03	84.57	39.32	57.36
MLB2017.05	66.77	84.54	39.21	57.81
MCB2017.05	66.7	83.4	39.8	58.5
QGHC+Att+Concat2018.08	65.89	83.54	38.06	57.1
MFB+CoAtt2018.08	65.1	83.2	38.8	55.5
MLB+Att2018.08	65.08	84.02	37.9	54.77
EENMN2018.08	64.9	—	—	—
End-to-End Module Networks (policy search after cloning)2017.04	64.9	—	—	—
MCB2017.04	64.7	—	—	—
MFB+Att2018.08	64.6	82.5	38.3	55.2
Ours2017.04	64.5	82.2	39.1	55.2
DAN2017.04	64.3	83	39.1	53.9
DAN2018.08	64.3	83	39.1	53.9
MCB2017.04	64.2	82.2	37.7	54.8
MCB+Att2018.08	64.2	82.2	37.7	54.8
End-to-End Module Networks (cloning expert)2017.04	64.2	—	—	—
RAU2017.04	63.3	81.9	39	53
RAU2018.08	63.3	81.9	39	53
MODERN2018.08	62.16	81.38	36.06	51.64
DAN2017.04	62	82.1	38.2	50.2
End-to-End Module Networks (cloning expert)2017.04	61.9	—	—	—
HieCoAtt2017.04	61.8	79.7	38.7	51.7
MHieCoAtt2018.08	61.8	79.7	38.7	51.7
HieCoAtt2017.05	61.8	79.7	38.7	51.7
MRN2017.04	61.7	82.3	38.8	49.3
MRN2017.05	61.68	82.28	38.82	49.25
DMN+2017.04	60.3	80.5	36.8	48.3
MRN2018.08	59.4	80.81	35.91	46.43
DNMN2018.08	59.4	81.1	38.6	45.4
D-NMN2017.05	59.4	81.1	38.6	45.5
ACK2017.04	59.2	81	38.4	45.2
ACK2017.05	59.17	81.01	38.42	45.23
SAN2017.04	58.7	79.3	36.6	46.1
SAN2018.08	58.7	79.3	36.6	46.1
SAN2017.05	58.7	79.3	36.6	46.1
NMN2017.04	58.6	81.2	38	44
NMN2018.08	58.6	81.2	38	44
Ask Your Neur.2017.05	58.39	78.39	36.45	46.28
SMem2018.08	58	80.9	37.3	43.1
SMem 2-hop2017.05	57.99	80.87	37.32	43.12
D-NMN2017.04	57.9	—	—	—
VQA team2017.04	57.8	80.5	36.8	43.1
NMN2017.04	57.3	—	—	—