Multimodal Text and Image Classification on VALSE spatial relations
Metric: pairwise accuracy (higher is better)
Metric: pairwise accuracy (higher is better)
| # | Model↕ | pairwise accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GPT1 | 77.2 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 2 | GPT2 | 75 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 3 | ViLBERT 12-in-1 | 67.7 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 4 | CLIP | 64.3 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 5 | LXMERT | 60.2 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 6 | ViLBERT | 57.2 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 7 | VisualBERT | 39.7 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |