Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917340519596032 |
|---|---|
| author | Borodin, Kirill Kondrashov, Kirill Vasiliev, Nikita Gladkova, Ksenia Larina, Inna Gorodnichev, Mikhail Mkrtchian, Grach |
| author_facet | Borodin, Kirill Kondrashov, Kirill Vasiliev, Nikita Gladkova, Ksenia Larina, Inna Gorodnichev, Mikhail Mkrtchian, Grach |
| contents | CCTV safety monitoring demands anomaly detectors combine reliable clip-level accuracy with predictable per-clip latency despite weak supervision. This work investigates compact vision-language models (VLMs) as practical detectors for this regime. A unified evaluation protocol standardizes preprocessing, prompting, dataset splits, metrics, and runtime settings to compare parameter-efficiently adapted compact VLMs against training-free VLM pipelines and weakly supervised baselines. Evaluation spans accuracy, precision, recall, F1, ROC-AUC, and average per-clip latency to jointly quantify detection quality and efficiency. With parameter-efficient adaptation, compact VLMs achieve performance on par with, and in several cases exceeding, established approaches while retaining competitive per-clip latency. Adaptation further reduces prompt sensitivity, producing more consistent behavior across prompt regimes under the shared protocol. These results show that parameter-efficient fine-tuning enables compact VLMs to serve as dependable clip-level anomaly detectors, yielding a favorable accuracy-efficiency trade-off within a transparent and consistent experimental setup. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13306 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision Borodin, Kirill Kondrashov, Kirill Vasiliev, Nikita Gladkova, Ksenia Larina, Inna Gorodnichev, Mikhail Mkrtchian, Grach Computer Vision and Pattern Recognition Machine Learning CCTV safety monitoring demands anomaly detectors combine reliable clip-level accuracy with predictable per-clip latency despite weak supervision. This work investigates compact vision-language models (VLMs) as practical detectors for this regime. A unified evaluation protocol standardizes preprocessing, prompting, dataset splits, metrics, and runtime settings to compare parameter-efficiently adapted compact VLMs against training-free VLM pipelines and weakly supervised baselines. Evaluation spans accuracy, precision, recall, F1, ROC-AUC, and average per-clip latency to jointly quantify detection quality and efficiency. With parameter-efficient adaptation, compact VLMs achieve performance on par with, and in several cases exceeding, established approaches while retaining competitive per-clip latency. Adaptation further reduces prompt sensitivity, producing more consistent behavior across prompt regimes under the shared protocol. These results show that parameter-efficient fine-tuning enables compact VLMs to serve as dependable clip-level anomaly detectors, yielding a favorable accuracy-efficiency trade-off within a transparent and consistent experimental setup. |
| title | Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2603.13306 |