AI Frontier Lectures
May 15, 2025 · Artificial Intelligence
DefMamba: How Deformable Scanning Boosts Vision State‑Space Models
DefMamba introduces a deformable visual state‑space model that dynamically adjusts scanning paths and reference points, preserving spatial structure and improving feature capture, achieving state‑of‑the‑art results on ImageNet classification, COCO detection, and ADE20K segmentation while reducing computational cost.
DefMambaDeformable ScanningState Space Model
0 likes · 23 min read