Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection

ArXi:2603.27661v1 Announce Type: new Edge detection is a fundamental image analysis task that underpins numerous high-level vision applications. Recent advances in Transformer architectures have significantly improved edge quality by capturing long-range dependencies, but this often comes with computational overhead. Achieving higher pixel-level accuracy requires increased input resolution, further escalating computational cost and limiting practical deployment.