Multiple-choice Visual Question Answering on VQA (test-dev)
70.2Accuracy (All)Ensemble of 7 Att. models
Evaluation results
| Method | Links | |
|---|---|---|
| Ensemble of 7 Att. modelsTraining Split=train+val2016.06 | 70.2 | |
| MCB + Att. + GloVe + GenomeTraining Split=train+val2016.06 | 69.9 | |
| MCB + Att. + GenomeTraining Split=train+val2016.06 | 69.5 | |
| Naver Labs (challenge 2nd)Training Split=train+val2016.06 | 69.4 | |
| MCB + Att. + GloVeTraining Split=train+val2016.06 | 69.1 | |
| MCB + Att.Training Split=train+val2016.06 | 68.6 | |
| MCB + GenomeTraining Split=train+val2016.06 | 66.4 | |
| HieCoAttTraining Split=train+val2016.06 | 65.8 | |
| MCBTraining Split=train+val2016.06 | 65.4 | |
| VQA teamTraining Split=train+val2016.06 | 62.7 |