Rethinking Unsupervised Outlier Detection via Multiple Thresholding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913429804023808 |
|---|---|
| author | Liu, Zhonghang Lu, Panzhong Xie, Guoyang Lu, Zhichao Lin, Wen-Yan |
| author_facet | Liu, Zhonghang Lu, Panzhong Xie, Guoyang Lu, Zhichao Lin, Wen-Yan |
| contents | In the realm of unsupervised image outlier detection, assigning outlier scores holds greater significance than its subsequent task: thresholding for predicting labels. This is because determining the optimal threshold on non-separable outlier score functions is an ill-posed problem. However, the lack of predicted labels not only hiders some real applications of current outlier detectors but also causes these methods not to be enhanced by leveraging the dataset's self-supervision. To advance existing scoring methods, we propose a multiple thresholding (Multi-T) module. It generates two thresholds that isolate inliers and outliers from the unlabelled target dataset, whereas outliers are employed to obtain better feature representation while inliers provide an uncontaminated manifold. Extensive experiments verify that Multi-T can significantly improve proposed outlier scoring methods. Moreover, Multi-T contributes to a naive distance-based method being state-of-the-art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05382 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Unsupervised Outlier Detection via Multiple Thresholding Liu, Zhonghang Lu, Panzhong Xie, Guoyang Lu, Zhichao Lin, Wen-Yan Computer Vision and Pattern Recognition In the realm of unsupervised image outlier detection, assigning outlier scores holds greater significance than its subsequent task: thresholding for predicting labels. This is because determining the optimal threshold on non-separable outlier score functions is an ill-posed problem. However, the lack of predicted labels not only hiders some real applications of current outlier detectors but also causes these methods not to be enhanced by leveraging the dataset's self-supervision. To advance existing scoring methods, we propose a multiple thresholding (Multi-T) module. It generates two thresholds that isolate inliers and outliers from the unlabelled target dataset, whereas outliers are employed to obtain better feature representation while inliers provide an uncontaminated manifold. Extensive experiments verify that Multi-T can significantly improve proposed outlier scoring methods. Moreover, Multi-T contributes to a naive distance-based method being state-of-the-art. |
| title | Rethinking Unsupervised Outlier Detection via Multiple Thresholding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.05382 |