Metraipolis › archive › dc_25bbe65ab2af

Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection — arXiv:2609.07229

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07229
License (as archived)
CC0-1.0
Archived
2026-10-16T15:11:44.832Z
SHA-256 of the archived text
492598b35f46914986342eaa6ba970e6f6e6ec814af7a609e213b0307a2ee6da
Stable URL of this page
https://metraipolis.com/documento/dc_25bbe65ab2af

How to cite

Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection — arXiv:2609.07229 — arXiv (en), https://arxiv.org/abs/2609.07229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25bbe65ab2af (Metraipolis archive dc_25bbe65ab2af, sha256 492598b35f46914986342eaa6ba970e6f6e6ec814af7a609e213b0307a2ee6da)
BibTeX
@misc{dc25bbe65ab2af,
  title = {Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection — arXiv:2609.07229},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07229},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25bbe65ab2af; sha256 492598b35f46914986342eaa6ba970e6f6e6ec814af7a609e213b0307a2ee6da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models offer a promising approach for zero-shot anomaly detection (ZSAD). However, due to object-centric bias, normal and anomalous text prototypes exhibit a high semantic overlap. While enforcing strict orthogonality between them improves discriminability, mapping highly contiguous visual inputs onto drastically orthogonal prototypes introduces a geometric dilemma, disrupting the pre-trained structural continuity. To address this problem, we propose Proximity-CLIP, a framework that visually calibrates the semantic margin to guide visual adaptation. First, we introduce a visually-calibrated semantic proximity learning mechanism that uses a bounded dynamic regularization to learn an appropriate semantic margin, ensuring discriminative separation while preserving structural alignment. Second, we design an Anomaly Query Module (AQM) driven by these text priors. Using the calibrated anomalous prototype as a semantic query, the AQM actively retrieves localized defect cues from contextual visual patches, mitigating the dilution of subtle anomalies during global pooling. Extensive experiments demonstrate that Proximity-CLIP outperforms current state-of-the-art methods across multiple ZSAD benchmarks with minimal architectural modifications.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.07229 — 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 2026-10-16T14:49:57.204Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).