Path-Conditioned Attention Mobility: From Depth to Execution Hubs in SegFormer
arXiv:2610.23893v1 Announce Type: new Abstract: Transformer compression often couples two distinct quantities: retained attention capacity and the number of sequential depths at which that capacity is executed. We study whether useful attention functions in a hierarchical vision transformer are loc…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-20 04:00 · arXiv cs.CV
Path-Conditioned Attention Mobility: From Depth to Execution Hubs in SegFormer