Toys4K
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Low-shot recognition | Toys4K (test) | Accuracy84.13 | 72 | |
| Low-shot recognition | Toys4k multi-object setting (test) | LSA60.49 | 15 | |
| Text-to-3D | Toys4k | CLIP Score29.3 | 14 | |
| Refining VFM-derived artifacts | Toys4k | mIoU44.6 | 13 | |
| 3D Geometry Synthesis | Toys4K (test) | Throughput (iter/s)0.6426 | 12 | |
| Multi-object Category Recognition (Categ-MObj) | Toys4k multi-object setting | LSA60.49 | 10 | |
| Shape-conditioned 3D object generation (geometric primitives) | Toys4K generalization (test) | CD4.89 | 9 | |
| Image-to-3D | Toys4k | FD (Inception)9.35 | 8 | |
| Low-shot object recognition | Toys4k Inst-SObj | Accuracy96.5 | 6 | |
| Low-shot recognition | Toys4k Categ-SObj 1.0 (test) | Accuracy79.69 | 6 | |
| Low-shot recognition | Toys4k Inst-SObj 1.0 (test) | Accuracy96.5 | 6 | |
| Multi-object Category Recognition with Support Assignment (Categ-MObj-SuppAssign) | Toys4k multi-object setting | LSA45.91 | 5 | |
| Low-Shot Mutual Exclusivity | Toys4k (test) | LSA0.477 | 3 | |
| Low-shot recognition | Toys4k LSME variant | LSA47.7 | 3 |
Showing 14 of 14 rows