Text-to-Depth Retrieval on SUN to NYU (test) (via Vision pivot)
36.1mAPLB+BB
Evaluation Results
| Method | Links | |
|---|---|---|
| LB+BBBackbone=LanguageBind, Variant=BrokenBind2026.02 | 36.1 | |
| IB+BBBackbone=ImageBind, Variant=BrokenBind2026.02 | 35.5 | |
| LB+FTBackbone=LanguageBind, Variant=Fine-tuned2026.02 | 14 | |
| IB+FTBackbone=ImageBind, Variant=Fine-tuned2026.02 | 12.4 | |
| LBBackbone=LanguageBind, Variant=Zero-shot2026.02 | 11.5 | |
| IBBackbone=ImageBind, Variant=Zero-shot2026.02 | 10 |