Metraipolis › archive › dc_135ebfaee660

A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection — arXiv:2608.21244

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.21244
License (as archived): CC0-1.0
Archived: 2026-10-18T10:56:25.294Z
SHA-256 of the archived text: 0a9dc50d549b91342846e88bf966429416e94e24d28681259684eeb29024bd07
Stable URL of this page: https://metraipolis.com/documento/dc_135ebfaee660

How to cite

A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection — arXiv:2608.21244 — arXiv (en), https://arxiv.org/abs/2608.21244 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_135ebfaee660 (Metraipolis archive dc_135ebfaee660, sha256 0a9dc50d549b91342846e88bf966429416e94e24d28681259684eeb29024bd07)

BibTeX

@misc{dc135ebfaee660,
  title = {A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection — arXiv:2608.21244},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21244},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_135ebfaee660; sha256 0a9dc50d549b91342846e88bf966429416e94e24d28681259684eeb29024bd07},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21244. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Anomaly detection aims to identify observations that deviate from normal patterns. Recent work has increasingly used pretrained vision--language models (VLMs) for training-free image and video anomaly detection without task-specific retraining. Anomaly detection is commonly evaluated by how well anomaly scores rank anomalous images or video frames above normal ones. Generative VLMs, however, assign probabilities to possible answers and then decode a single answer. This decoding step may discard ordering information. We call this loss decoded-answer rank compression. To isolate this effect, we compare two ways of scoring the same VLM output: one uses only the decoded answer, while the other computes a probability-weighted score over all possible answers. Probability-weighted scoring consistently outperforms decoded-answer scoring across image and video anomaly detection benchmarks, using different VLMs and answer scales. The mean gains range from 7.66 to 19.95 points on the primary metrics. Most of this gap comes from decoded-answer ties. Breaking decoded-answer ties with answer probabilities recovers at least 95% of the average performance gap on every benchmark. We further investigate how these ties affect evaluation. We find that evaluating tied scores one input at a time makes the reported AUROC depend on input order, and that linear PR interpolation can inflate reported performance. These results reveal that both how VLM outputs are scored and how discrete anomaly scores are evaluated affect reported anomaly-detection performance.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.21244 — 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 2026-10-18T10:48:13.605Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).