Image Outlier Detection Without Training using RANSAC
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911826870009856 |
|---|---|
| author | Tsai, Chen-Han Peng, Yu-Shao |
| author_facet | Tsai, Chen-Han Peng, Yu-Shao |
| contents | Image outlier detection (OD) is an essential tool to ensure the quality of images used in computer vision tasks. Existing algorithms often involve training a model to represent the inlier distribution, and outliers are determined by some deviation measure. Although existing methods proved effective when trained on strictly inlier samples, their performance remains questionable when undesired outliers are included during training. As a result of this limitation, it is necessary to carefully examine the data when developing OD models for new domains. In this work, we present a novel image OD algorithm called RANSAC-NN that eliminates the need of data examination and model training altogether. Unlike existing approaches, RANSAC-NN can be directly applied on datasets containing outliers by sampling and comparing subsets of the data. Our algorithm maintains favorable performance compared to existing methods on a range of benchmarks. Furthermore, we show that RANSAC-NN can enhance the robustness of existing methods by incorporating our algorithm as part of the data preparation process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_12301 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Image Outlier Detection Without Training using RANSAC Tsai, Chen-Han Peng, Yu-Shao Computer Vision and Pattern Recognition Information Retrieval Machine Learning Image outlier detection (OD) is an essential tool to ensure the quality of images used in computer vision tasks. Existing algorithms often involve training a model to represent the inlier distribution, and outliers are determined by some deviation measure. Although existing methods proved effective when trained on strictly inlier samples, their performance remains questionable when undesired outliers are included during training. As a result of this limitation, it is necessary to carefully examine the data when developing OD models for new domains. In this work, we present a novel image OD algorithm called RANSAC-NN that eliminates the need of data examination and model training altogether. Unlike existing approaches, RANSAC-NN can be directly applied on datasets containing outliers by sampling and comparing subsets of the data. Our algorithm maintains favorable performance compared to existing methods on a range of benchmarks. Furthermore, we show that RANSAC-NN can enhance the robustness of existing methods by incorporating our algorithm as part of the data preparation process. |
| title | Image Outlier Detection Without Training using RANSAC |
| topic | Computer Vision and Pattern Recognition Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2307.12301 |