Image Captioning on COCO (test) (CIDEr Metric)
149.2CIDErPALI-X-55B
Evaluation Results
| Method | Links | |
|---|---|---|
| PALI-X-55Bmode=per-task finetuning2023.07 | 149.2 | |
| PerceptionGPT2023.11 | 123.2 | |
| Unified-IO2023.11 | 122.1 | |
| Emu-Izero-shot=true, instruction_tuned=true2023.07 | 120.4 | |
| Shikra2023.11 | 117.5 | |
| MM1Size=7B, Architecture=fully autoregressive, # tokens per image=144, Few-shot=8 random in-context examples2024.05 | 116.3 | |
| Idefics2-baseSize=8B, Architecture=fully autoregressive, # tokens per image=64, Few-shot=8 random in-context examples2024.05 | 116 | |
| VPGTrans2023.11 | 114.2 | |
| Emuzero-shot=true, prompt_strategy=Chain-of-Thought2023.07 | 112.4 | |
| FlamingoSize=9B, Architecture=cross-attention, Few-shot=8 random in-context examples2024.05 | 99 | |
| Idefics1Size=9B, Architecture=cross-attention, Few-shot=8 random in-context examples2024.05 | 97 | |
| OpenFlamingoSize=9B, Architecture=cross-attention, Few-shot=8 random in-context examples2024.05 | 96.3 | |
| Kosmos-12023.11 | 84.7 | |
| Kosmos-1zero-shot=true2023.07 | 84.7 | |
| FM-80B2023.11 | 84.3 | |
| MetaLMzero-shot=true2023.07 | 82.2 | |
| FM-9B2023.11 | 79.4 | |
| Flamingo-9Bzero-shot=true, prompt_strategy=2-example text-only prompt2023.07 | 79.4 |