Our new X account is live! Follow @wizwand_team for updates

Open-Ended Visual Question Answering on VQA 1.0 (test-dev)

66.7Overall Accuracy

Ensemble of 7 Att. models

Updated 3d ago

Evaluation Results

Method
Ensemble of 7 Att. models 2016.06	66.7	83.4	39.8	58.5
Dual-MFA 2017.11	66.01	83.59	40.18	56.84
RelAtt 2018.05	65.69	83.55	36.92	56.94
MCB + Att. + GloVe + Genome 2016.06	65.4	82.3	37.2	57.4
Dual-MLB 2017.11	65.12	83.32	39.96	55.26
MCB + Att. + Genome 2016.06	65.1	81.7	38.2	57
Naver Labs (challenge 2nd) 2016.06	64.9	83.5	39.8	54.8
MLB 2017.11	64.89	84.13	37.85	54.57
MCB + Att. + GloVe 2016.06	64.7	82.5	37.6	55.6
Fukui et al. 2016 ResNet* 2016.06	64.7	82.5	37.6	55.6
MCB 2017.11	64.7	82.5	37.6	55.6
MLAN 2018.05	64.6	83.8	40.2	53.7
MLB 2018.05	64.53	83.41	37.82	54.43
DAN 2016.11	64.3	83	39.1	53.9
MCB 2018.05	64.2	82.2	37.7	54.8
MCB + Att. 2016.06	64.2	82.2	37.7	54.8
MCB 2016.11	64.2	82.2	37.7	54.8
Ours ResNet 2016.06	63.3	81.9	39	53
RAU 2016.11	63.3	81.9	39	53
VQA-Machine 2017.11	63.1	81.5	38.4	53
MCB + Genome 2016.06	62.3	81.7	36.6	51.5
DAN 2016.11	62	82.1	38.2	50.2
HieCoAtt 2016.06	61.8	79.7	38.7	51.7
Lu et al. 2016 ResNet* 2016.06	61.8	79.7	38.7	51.7
HieCoAtt 2016.11	61.8	79.7	38.7	51.7
HieCoAtt 2017.11	61.8	79.7	38.7	51.7
Kim et al. 2016 ResNet* 2016.06	61.7	82.3	38.8	49.3
MRN 2016.11	61.7	82.3	38.8	49.3
MRN 2016.06	61.68	82.28	38.82	49.25
MRN 2018.05	61.68	82.28	38.82	49.25
MRN 2017.11	61.68	82.28	38.82	49.25
MRN 2016.06	61.47	82.28	39.09	48.76
MRN 2016.06	61.45	82.36	38.4	48.81
Ours_FULL 2016.06	61.3	81.5	37	49.6
Ours_MS 2016.06	61	81.3	36.8	49.1
MCB 2016.06	60.8	81.2	35.1	49.3
MRN 2016.06	60.77	82.1	39.11	47.46
QRU 2018.05	60.72	82.29	37.02	47.67
QRU 2017.11	60.72	82.29	37.02	47.67
MRN 2016.06	60.68	82.4	38.69	47.1
MRN 2016.06	60.53	82.53	38.34	46.78
DMN+ 2016.06	60.3	80.5	36.8	48.3
DMN+ 2018.05	60.3	80.5	36.8	48.3
DMN+ 2016.06	60.3	80.5	36.8	48.3
Xiong, Merity, and Socher 2016 2016.06	60.3	80.5	36.8	48.3
DMN+ 2016.11	60.3	80.5	36.8	48.3
DMN+ 2017.11	60.3	80.5	36.8	48.3
D-NMN 2016.06	59.4	81.1	38.6	45.5
FDA 2016.06	59.24	81.14	36.16	45.77
FDA 2018.05	59.24	81.14	36.16	45.77
FDA 2017.11	59.24	81.14	36.16	45.77
FDA 2016.06	59.2	81.1	36.2	45.8
AMA 2016.06	59.2	81	38.4	45.2
Wu et al. 2016 2016.06	59.2	81	38.4	45.2
ACK 2016.11	59.2	81	38.4	45.2
ACK 2016.06	59.17	81.01	38.42	45.23
AMA 2018.05	59.17	81.01	38.42	45.23
Ours_SS 2016.06	59	78.3	37.1	47.6
SAN 2016.06	58.7	79.3	36.6	46.1
SAN 2018.05	58.7	79.3	36.6	46.1
SAN 2016.06	58.7	79.3	36.6	46.1
Yang et al. 2016 2016.06	58.7	79.3	36.6	46.1
SAN 2016.11	58.7	79.3	36.6	46.1
SAN 2017.11	58.7	79.3	36.6	46.1
NMN 2016.06	58.6	81.2	38	44
NMN 2016.11	58.6	81.2	38	44
AYN 2016.06	58.4	78.4	36.4	46.3
Deep Q+I 2016.06	58.02	80.87	36.46	43.4
SMem 2016.06	58	80.9	37.3	43.1
SMem 2018.05	57.99	80.87	37.32	43.12
SMem 2017.11	57.99	80.87	37.32	43.12
D-NMN 2016.06	57.9	80.5	37.4	43.1
Andreas et al. 2016b 2016.06	57.9	80.5	37.4	43.1
VQA team 2016.06	57.8	80.5	36.8	43.1
Antol et al. 2015 2016.06	57.8	80.5	36.8	43.1
VQA team 2016.11	57.8	80.5	36.8	43.1
V2L 2018.05	57.46	78.9	36.11	40.07
Andreas et al. 2016a 2016.06	57.3	79.7	37.3	39.3
DPPnet 2016.06	57.22	80.71	37.24	41.69
DPPnet 2018.05	57.22	80.71	37.24	41.69
DPPnet 2017.11	57.22	80.71	37.24	41.69
DPPnet 2016.06	57.2	80.7	37.2	41.7
Noh, Seo, and Han 2016 2016.06	57.2	80.7	37.2	41.7
DPPnet 2016.11	57.2	80.7	37.2	41.7
iBOWING 2017.11	55.72	76.55	35.03	42.62
iBOWIMG 2016.06	55.7	76.5	35	42.6
Zhou et al. 2015 2016.06	55.7	76.6	35	42.6
iBOWIMG 2016.11	55.7	76.5	35	42.6
LSTM Q+I 2016.06	53.74	78.94	35.24	36.42
LSTM Q+I 2018.05	53.74	78.94	35.24	36.42
LSTM Q+I 2017.11	53.74	78.94	35.24	36.42
LSTM Q+I (Antol et al. 2015) 2016.06	53.7	78.9	35.2	36.4
Q+I 2016.06	52.64	75.55	33.67	37.37
Bow Q+I (Antol et al. 2015) 2016.06	52.6	75.6	33.7	37.4
LSTM Q (Antol et al. 2015) 2016.06	48.8	78.2	35.7	26.6
LSTM Q 2016.06	48.76	78.2	35.68	26.59
BOW Q (Antol et al. 2015) 2016.06	48.1	75.7	36.7	27.1
Question 2016.06	48.09	75.66	36.7	27.14
Image 2016.06	28.13	64.01	0.42	3.77
I (Antol et al. 2015) 2016.06	28.1	64	0.4	3.8