Robust Novelty Detection through Style-Conscious Feature Ranking
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910806342369280 |
|---|---|
| author | Smeu, Stefan Burceanu, Elena Haller, Emanuela Nicolicioiu, Andrei Liviu |
| author_facet | Smeu, Stefan Burceanu, Elena Haller, Emanuela Nicolicioiu, Andrei Liviu |
| contents | Novelty detection seeks to identify samples deviating from a known distribution, yet data shifts in a multitude of ways, and only a few consist of relevant changes. Aligned with out-of-distribution generalization literature, we advocate for a formal distinction between task-relevant semantic or content changes and irrelevant style changes. This distinction forms the basis for robust novelty detection, emphasizing the identification of semantic changes resilient to style distributional shifts. To this end, we introduce Stylist, a method that utilizes pretrained large-scale model representations to selectively discard environment-biased features. By computing per-feature scores based on feature distribution distances between environments, Stylist effectively eliminates features responsible for spurious correlations, enhancing novelty detection performance. Evaluations on adapted domain generalization datasets and a synthetic dataset demonstrate Stylist's efficacy in improving novelty detection across diverse datasets with stylistic and content shifts. The code is available at https://github.com/bit-ml/Stylist. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_03738 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Robust Novelty Detection through Style-Conscious Feature Ranking Smeu, Stefan Burceanu, Elena Haller, Emanuela Nicolicioiu, Andrei Liviu Computer Vision and Pattern Recognition Machine Learning Novelty detection seeks to identify samples deviating from a known distribution, yet data shifts in a multitude of ways, and only a few consist of relevant changes. Aligned with out-of-distribution generalization literature, we advocate for a formal distinction between task-relevant semantic or content changes and irrelevant style changes. This distinction forms the basis for robust novelty detection, emphasizing the identification of semantic changes resilient to style distributional shifts. To this end, we introduce Stylist, a method that utilizes pretrained large-scale model representations to selectively discard environment-biased features. By computing per-feature scores based on feature distribution distances between environments, Stylist effectively eliminates features responsible for spurious correlations, enhancing novelty detection performance. Evaluations on adapted domain generalization datasets and a synthetic dataset demonstrate Stylist's efficacy in improving novelty detection across diverse datasets with stylistic and content shifts. The code is available at https://github.com/bit-ml/Stylist. |
| title | Robust Novelty Detection through Style-Conscious Feature Ranking |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2310.03738 |