Multimodal Text and Image Classification on VALSE counting small numbers
Metric: pairwise accuracy (higher is better)
Metric: pairwise accuracy (higher is better)
| # | Model↕ | pairwise accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ViLBERT 12-in-1 | 80.2 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 2 | LXMERT | 69.2 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 3 | ViLBERT | 62.9 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 4 | CLIP | 62.5 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 5 | GPT2 | 49.8 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 6 | GPT1 | 48.7 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 7 | VisualBERT | 48.2 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |