Multimodal Deep Learning on VALSE counting adversarial
Metric: pairwise accuracy (higher is better)
Metric: pairwise accuracy (higher is better)
| # | Model↕ | pairwise accuracy▼ | Augmentations | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ViLBERT 12-in-1 | 77.3 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 2 | ViLBERT | 73.7 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 3 | GPT1 | 69.5 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 4 | CLIP | 57.5 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 5 | VisualBERT | 50 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 6 | GPT2 | 45.3 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 7 | LXMERT | 42.6 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |