Rethinking Learnable Tree Filter for Generic Feature Transform Lin Song 1 Y anwei Li
–Neural Information Processing Systems
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance, hindering the effective long-range interactions.
Neural Information Processing Systems
Oct-2-2025, 13:03:01 GMT
- Country:
- Asia > China
- Beijing > Beijing (0.04)
- Guangxi Province > Nanning (0.04)
- Hong Kong (0.04)
- Shaanxi Province > Xi'an (0.04)
- North America > Canada (0.04)
- Asia > China
- Technology: