Metraipolis › archive › dc_e3f745fcadd4

Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display Images — arXiv:2609.05520

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05520
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:37.240Z
SHA-256 of the archived text
860ea79cfff1503169df2621087acbfc60638c0f30cef4a3dabec4d8ed4d1c30
Stable URL of this page
https://metraipolis.com/documento/dc_e3f745fcadd4

How to cite

Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display Images — arXiv:2609.05520 — arXiv (en), https://arxiv.org/abs/2609.05520 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3f745fcadd4 (Metraipolis archive dc_e3f745fcadd4, sha256 860ea79cfff1503169df2621087acbfc60638c0f30cef4a3dabec4d8ed4d1c30)
BibTeX
@misc{dce3f745fcadd4,
  title = {Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display Images — arXiv:2609.05520},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05520},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3f745fcadd4; sha256 860ea79cfff1503169df2621087acbfc60638c0f30cef4a3dabec4d8ed4d1c30},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05520. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we tackle automatic anomaly detection in multi-illumination and multi-focus display images. The minute defects on the display surface are hard to spot out in RGB images and by a model trained with only normal data. To address this, we propose a novel contrastive learning scheme for knowledge distillation-based anomaly detection. In our framework, Multiresolution Knowledge Distillation (MKD) is adopted as a baseline, which operates by measuring feature similarities between the teacher and student networks. Based on MKD, we propose a novel contrastive learning method, namely Multiresolution Contrastive Distillation (MCD), which does not require positive/negative pairs with an anchor but operates by pulling/pushing the distance between the teacher and student features. Furthermore, we propose the blending module that transforms and aggregate multi-channel information to the three-channel input layer of MCD. Our proposed method significantly outperforms competitive state-of-the-art methods in both AUROC and accuracy metrics on the collected Multi-illumination and Multi-focus display image dataset for Anomaly Detection (MMdAD).

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.05520 — 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 2026-10-16T13:39:43.113Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).