Image Captioning on MyVLM
0.975Caption Recall (Single)MC-LLaVA
Evaluation Results
| Method | Links | |
|---|---|---|
| MC-LLaVAT (Tokens)=10^1, Auxiliary Loss=true2024.11 | 0.975 | |
| MC-LLaVAT (Tokens)=10^1, Auxiliary Loss=false2024.11 | 0.972 | |
| PeKitT (Tokens)=02024.11 | 0.97 | |
| GPT4o+PromptT (Tokens)=10^12024.11 | 0.969 | |
| RAP-MLLMT (Tokens)=10^22024.11 | 0.937 | |
| Yo'LLaVA-ST (Tokens)=10^12024.11 | 0.931 | |
| Yo'LLaVA-MT (Tokens)=10^12024.11 | 0.931 | |
| MyVLMT (Tokens)=12024.11 | 0.921 | |
| LLaVA+PromptT (Tokens)=10^22024.11 | 0.211 | |
| LLaVA+PromptT (Tokens)=10^12024.11 | 0.207 | |
| LLaVAT (Tokens)=02024.11 | 0.021 |