LightCDNet-small
Reported on 3 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Methodology3 results
- 90.57best: 92.67 (MAE+MTP(ViT-L+RVSA))
- 82.77best: 85.76 (Changer (Ex, ResNeSt101))
- Params(M)0.35best: 335 (IMP+MTP(InternImage-XL))