SOURCE-LINKED INTELLIGENCE

DERA: Detached Edge-Residual Adaptation for Prohibited item Detection

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Prohibited-item detection in X-ray imagery remains challenging due to object superposition, weak texture, and material clutter which obscure both semantic appearance and object boundaries. We propose \textbf{DERA}, a \textbf{D}etached \textbf{E}dge-\textbf{R}esidual \textbf{A}daptation framework for prohibited item detection under X-ray imagery. DERA combines hierarchical visual features with a parallel pixel-difference edge pyramid and learns an object-specific boundary prior from training-time contours of the instance masks. The detached prior gates edge-sensitive features, which are injecte

Read original source ↗ Open in workspace

recordType

paper

region

Global