RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mirzaei, Hossein, Jafari, Mohammad, Dehbashi, Hamid Reza, Ansari, Ali, Ghobadi, Sepehr, Hadi, Masoud, Moakhar, Arshia Soltani, Azizmalayeri, Mohammad, Baghshah, Mahdieh Soleymani, Rohban, Mohammad Hossein
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916586870276096
author Mirzaei, Hossein
Jafari, Mohammad
Dehbashi, Hamid Reza
Ansari, Ali
Ghobadi, Sepehr
Hadi, Masoud
Moakhar, Arshia Soltani
Azizmalayeri, Mohammad
Baghshah, Mahdieh Soleymani
Rohban, Mohammad Hossein
author_facet Mirzaei, Hossein
Jafari, Mohammad
Dehbashi, Hamid Reza
Ansari, Ali
Ghobadi, Sepehr
Hadi, Masoud
Moakhar, Arshia Soltani
Azizmalayeri, Mohammad
Baghshah, Mahdieh Soleymani
Rohban, Mohammad Hossein
contents In recent years, there have been significant improvements in various forms of image outlier detection. However, outlier detection performance under adversarial settings lags far behind that in standard settings. This is due to the lack of effective exposure to adversarial scenarios during training, especially on unseen outliers, leading to detection models failing to learn robust features. To bridge this gap, we introduce RODEO, a data-centric approach that generates effective outliers for robust outlier detection. More specifically, we show that incorporating outlier exposure (OE) and adversarial training can be an effective strategy for this purpose, as long as the exposed training outliers meet certain characteristics, including diversity, and both conceptual differentiability and analogy to the inlier samples. We leverage a text-to-image model to achieve this goal. We demonstrate both quantitatively and qualitatively that our adaptive OE method effectively generates ``diverse'' and ``near-distribution'' outliers, leveraging information from both text and image domains. Moreover, our experimental results show that utilizing our synthesized outliers significantly enhances the performance of the outlier detector, particularly in adversarial settings.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16971
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
Mirzaei, Hossein
Jafari, Mohammad
Dehbashi, Hamid Reza
Ansari, Ali
Ghobadi, Sepehr
Hadi, Masoud
Moakhar, Arshia Soltani
Azizmalayeri, Mohammad
Baghshah, Mahdieh Soleymani
Rohban, Mohammad Hossein
Computer Vision and Pattern Recognition
Machine Learning
In recent years, there have been significant improvements in various forms of image outlier detection. However, outlier detection performance under adversarial settings lags far behind that in standard settings. This is due to the lack of effective exposure to adversarial scenarios during training, especially on unseen outliers, leading to detection models failing to learn robust features. To bridge this gap, we introduce RODEO, a data-centric approach that generates effective outliers for robust outlier detection. More specifically, we show that incorporating outlier exposure (OE) and adversarial training can be an effective strategy for this purpose, as long as the exposed training outliers meet certain characteristics, including diversity, and both conceptual differentiability and analogy to the inlier samples. We leverage a text-to-image model to achieve this goal. We demonstrate both quantitatively and qualitatively that our adaptive OE method effectively generates ``diverse'' and ``near-distribution'' outliers, leveraging information from both text and image domains. Moreover, our experimental results show that utilizing our synthesized outliers significantly enhances the performance of the outlier detector, particularly in adversarial settings.
title RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2501.16971