Visual Question Answering on CLEVR-CoGenT systematic generalization 1.0 (test)
77.3AccuracyVector-NMN
Evaluation results
| Method | Links | |
|---|---|---|
| Vector-NMNNMN architecture=Vector-NMN, Image encoder type=group2021.06 | 77.3 | |
| Vector-NMNNMN architecture=Vector-NMN, Image encoder type=all2021.06 | 73.2 | |
| Tensor-NMNNMN architecture=Tensor-NMN, Image encoder type=all2021.06 | 72.7 |