Abstract:Video anomaly detection (VAD) systems often prioritize accuracy while overlooking privacy concerns, limiting their suitability for real-world deployment. We propose the Orthogonal Projection Layer (OPL), a lightweight module that removes task-irrelevant variations to produce representations focused on anomaly-relevant cues. To address privacy risks in human-centered scenarios, we introduce Guided OPL (G-OPL), which suppresses facial attributes using weak supervision from face-presence signals while preserving non-identifying features such as pose and motion. A cosine alignment objective enforces consistent capture and removal of facial information without identity labels or adversarial training. We further present a privacy-aware evaluation framework that jointly assesses detection performance and privacy preservation, and enables analysis of how sensitive information is filtered. Experiments show that embedding privacy constraints into model design reduces sensitive information while maintaining or improving detection accuracy, supporting projection-based architectures as a principled approach for privacy-aware VAD.
| Comments: | Accepted as a Spotlight paper at the Forty-Third International Conference on Machine Learning (ICML 2026) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.08651 [cs.CV] |
| (or arXiv:2605.08651v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08651 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lei Wang [view email]
[v1]
Sat, 9 May 2026 03:46:39 UTC (5,676 KB)