Metraipolis › archive › dc_58ab787d350f

DERA: Detached Edge-Residual Adaptation for Prohibited item Detection — arXiv:2609.12411

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12411
License (as archived)
CC0-1.0
Archived
2026-10-16T03:57:34.841Z
SHA-256 of the archived text
0dc0e7c311ea93c878a2ea7a804479ef54322e1457c334578454ee949c0a4b03
Stable URL of this page
https://metraipolis.com/documento/dc_58ab787d350f

How to cite

DERA: Detached Edge-Residual Adaptation for Prohibited item Detection — arXiv:2609.12411 — arXiv (en), https://arxiv.org/abs/2609.12411 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58ab787d350f (Metraipolis archive dc_58ab787d350f, sha256 0dc0e7c311ea93c878a2ea7a804479ef54322e1457c334578454ee949c0a4b03)
BibTeX
@misc{dc58ab787d350f,
  title = {DERA: Detached Edge-Residual Adaptation for Prohibited item Detection — arXiv:2609.12411},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12411},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58ab787d350f; sha256 0dc0e7c311ea93c878a2ea7a804479ef54322e1457c334578454ee949c0a4b03},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12411. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 injected into the early visual stages through residual heads. This staged design preserves the foundation detector at the start of adaptation, isolates boundary supervision from semantic feature learning, and restricts the final adaptation stage to only \(14.7\)K trainable parameters. Evaluated on PIDray, CLCXray, and STCray, DERA improves the baseline by \textbf{3.1}, \textbf{1.6}, and \textbf{2.4} AP points, respectively.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.12411 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T03:44:26.246Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).