Vision Understanding on LLaVA-Wild
74.2LLaVA-Wild AccuracyLLaVA-FastV (k=3, r=0.75)
Evaluation Results
| Method | Links | |
|---|---|---|
| LLaVA-FastV (k=3, r=0.75)LLM=Vicuna-13B, Res.=336, Token=144 (-75%), TFLOPS=6.0 (-69%)2024.12 | 74.2 | |
| Dynamic-LLaVA-13BILLM=Vicuna-13B, Res.=336, Token=115 (-80%), TFLOPS=4.7+0.01 (-76%)2024.12 | 73.4 | |
| LLaVA-1.5-13BLLM=Vicuna-13B, Res.=336, Token=576, TFLOPS=19.62024.12 | 72.5 | |
| Dynamic-LLaVA-13BITLLM=Vicuna-13B, Res.=336, Token=115 (-80%), TFLOPS=4.7+0.01 (-76%)2024.12 | 70.1 | |
| Dynamic-LLaVA-7BITLLM=Vicuna-7B, Res.=336, Token=115 (-80%), TFLOPS=2.5+0.01 (-75%)2024.12 | 68.7 | |
| Dynamic-LLaVA-7BILLM=Vicuna-7B, Res.=336, Token=115 (-80%), TFLOPS=2.5+0.01 (-75%)2024.12 | 67.3 | |
| LLaVA-FastV (k=3, r=0.75)LLM=Vicuna-7B, Res.=336, Token=144 (-75%), TFLOPS=3.2 (-68%)2024.12 | 66.7 | |
| LLaVA-1.5-7BLLM=Vicuna-7B, Res.=336, Token=576, TFLOPS=10.12024.12 | 65.8 |