Detecting Media Clones in Cultural Repositories Using a Positive Unlabeled Learning Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911568442163200 |
|---|---|
| author | Sevetlidis, V. Arampatzakis, V. Karta, M. Mourthos, I. Tsiafaki, D. Pavlidis, G. |
| author_facet | Sevetlidis, V. Arampatzakis, V. Karta, M. Mourthos, I. Tsiafaki, D. Pavlidis, G. |
| contents | We formulate curator-in-the-loop duplicate discovery in the AtticPOT repository as a Positive-Unlabeled (PU) learning problem. Given a single anchor per artefact, we train a lightweight per-query Clone Encoder on augmented views of the anchor and score the unlabeled repository with an interpretable threshold on the latent l_2 norm. The system proposes candidates for curator verification, uncovering cross-record duplicates that were not verified a priori. On CIFAR-10 we obtain F1=96.37 (AUROC=97.97); on AtticPOT we reach F1=90.79 (AUROC=98.99), improving F1 by +7.70 points over the best baseline (SVDD) under the same lightweight backbone. Qualitative "find-similar" panels show stable neighbourhoods across viewpoint and condition. The method avoids explicit negatives, offers a transparent operating point, and fits de-duplication, record linkage, and curator-in-the-loop workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04071 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Detecting Media Clones in Cultural Repositories Using a Positive Unlabeled Learning Approach Sevetlidis, V. Arampatzakis, V. Karta, M. Mourthos, I. Tsiafaki, D. Pavlidis, G. Computer Vision and Pattern Recognition We formulate curator-in-the-loop duplicate discovery in the AtticPOT repository as a Positive-Unlabeled (PU) learning problem. Given a single anchor per artefact, we train a lightweight per-query Clone Encoder on augmented views of the anchor and score the unlabeled repository with an interpretable threshold on the latent l_2 norm. The system proposes candidates for curator verification, uncovering cross-record duplicates that were not verified a priori. On CIFAR-10 we obtain F1=96.37 (AUROC=97.97); on AtticPOT we reach F1=90.79 (AUROC=98.99), improving F1 by +7.70 points over the best baseline (SVDD) under the same lightweight backbone. Qualitative "find-similar" panels show stable neighbourhoods across viewpoint and condition. The method avoids explicit negatives, offers a transparent operating point, and fits de-duplication, record linkage, and curator-in-the-loop workflows. |
| title | Detecting Media Clones in Cultural Repositories Using a Positive Unlabeled Learning Approach |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.04071 |