Visual Question Answering (VQA) on GQA test-std

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	ProTo	65.14	No	ProTo: Program-Guided Transformer for Program-Gu...	2021-10-02	Code
2	NSM	63.17	No	Learning by Abstraction: The Neural State Machine	2019-07-09	Code
3	MDETR-ENB5	62.45	No	MDETR -- Modulated Detection for End-to-End Mult...	2021-04-26	Code
4	LXMERT	60.3	Yes	LXMERT: Learning Cross-Modality Encoder Represen...	2019-08-20	Code
5	single-hop + LCGN (ours)	56.1	No	Language-Conditioned Graph Networks for Relation...	2019-05-10	Code
6	MAC	54.06	No	GQA: A New Dataset for Real-World Visual Reasoni...	2019-02-25	Code
7	CNN+LSTM	46.55	No	GQA: A New Dataset for Real-World Visual Reasoni...	2019-02-25	Code

#1ProToSOTA
65.14
Accuracy· 2021-10-02
ProTo: Program-Guided Transformer for Program-Guided Tasks Code
#2NSMSOTA
63.17
Accuracy· 2019-07-09
Learning by Abstraction: The Neural State Machine Code
#3MDETR-ENB5
62.45
Accuracy· 2021-04-26
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding Code
#4LXMERT
60.3
Accuracy· Extra Data· 2019-08-20
LXMERT: Learning Cross-Modality Encoder Representations from Transformers Code
#5single-hop + LCGN (ours)SOTA
56.1
Accuracy· 2019-05-10
Language-Conditioned Graph Networks for Relational Reasoning Code
#6MACSOTA
54.06
Accuracy· 2019-02-25
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering Code
#7CNN+LSTM
46.55
Accuracy· 2019-02-25
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering Code