Visual Question Answering on TallyQA complex
77.1AccuracySMoLA-PaLI-X_FT (Specialist)
Evaluation Results
| Method | Links | |
|---|---|---|
| SMoLA-PaLI-X_FT (Specialist)Base model=PaLI-X, Per-task LoRA tuning=true, LoRA rank=42023.12 | 77.1 | |
| PaLI-XParameters=55B, Fine-tuning=per-task, OCR_pipeline=without2023.05 | 75.6 | |
| PaLI-XNumber of parameters=55B2023.05 | 75.6 | |
| PaLI-XParameters=55B2023.10 | 75.6 | |
| PaLI-XBase model=PaLI-X2023.12 | 75.6 | |
| SOTA [7]2023.12 | 75.6 | |
| PaLIParameters=17B, Fine-tuning=per-task, OCR_pipeline=without2023.05 | 70.9 | |
| PaLINumber of parameters=17B2023.05 | 70.9 | |
| PaLI-17BParameters=17B2023.10 | 70.9 | |
| PaLI-3Parameters=5B2023.10 | 70.5 | |
| MoVieFine-tuning=per-task, OCR_pipeline=without2023.05 | 56.8 | |
| MoVie2023.05 | 56.8 | |
| MoVie2023.10 | 56.8 |