InDiD: Instant Disorder Detection via Representation Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916928329613312 |
|---|---|
| author | Romanenkova, Evgenia Stepikin, Alexander Morozov, Matvey Zaytsev, Alexey |
| author_facet | Romanenkova, Evgenia Stepikin, Alexander Morozov, Matvey Zaytsev, Alexey |
| contents | For sequential data, a change point is a moment of abrupt regime switch in data streams. Such changes appear in different scenarios, including simpler data from sensors and more challenging video surveillance data. We need to detect disorders as fast as possible. Classic approaches for change point detection (CPD) might underperform for semi-structured sequential data because they cannot process its structure without a proper representation. We propose a principled loss function that balances change detection delay and time to a false alarm. It approximates classic rigorous solutions but is differentiable and allows representation learning for deep models. We consider synthetic sequences, real-world data sensors and videos with change points. We carefully labelled available data with change point moments for video data and released it for the first time. Experiments suggest that complex data require meaningful representations tailored for the specificity of the CPD task -- and our approach provides them outperforming considered baselines. For example, for explosion detection in video, the F1 score for our method is 0.53 compared to baseline scores of 0.31 and 0.35. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_02602 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | InDiD: Instant Disorder Detection via Representation Learning Romanenkova, Evgenia Stepikin, Alexander Morozov, Matvey Zaytsev, Alexey Machine Learning For sequential data, a change point is a moment of abrupt regime switch in data streams. Such changes appear in different scenarios, including simpler data from sensors and more challenging video surveillance data. We need to detect disorders as fast as possible. Classic approaches for change point detection (CPD) might underperform for semi-structured sequential data because they cannot process its structure without a proper representation. We propose a principled loss function that balances change detection delay and time to a false alarm. It approximates classic rigorous solutions but is differentiable and allows representation learning for deep models. We consider synthetic sequences, real-world data sensors and videos with change points. We carefully labelled available data with change point moments for video data and released it for the first time. Experiments suggest that complex data require meaningful representations tailored for the specificity of the CPD task -- and our approach provides them outperforming considered baselines. For example, for explosion detection in video, the F1 score for our method is 0.53 compared to baseline scores of 0.31 and 0.35. |
| title | InDiD: Instant Disorder Detection via Representation Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2106.02602 |