RODEO: Robust Out-of-Distribution Detection Via Exposing Adaptive Outliers

Hossein Mirzaei, Mohammad Jafari, Hamid Reza Dehbashi, Ali Ansari, Sepehr Ghobadi, Masoud Hadi, Arshia Soltani Moakhar, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Out-of-Distribution Detection, Adversarial Robustness, Robust Anomaly Detection, Outlier Exposure, Generative Models

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Detecting out-of-distribution (OOD) input samples at the time of inference is a key element in the trustworthy deployment of intelligent models. While there has been tremendous improvement in various variants of OOD detection in recent years, detection performance under adversarial settings lags far behind the performance in the standard setting. In order to bridge this gap, we introduce RODEO in this paper, a data-centric approach that generates effective outliers for robust OOD detection. More specifically, we first show that targeting the classification of adversarially perturbed in- and out-of-distribution samples through outlier exposure (OE) could be an effective strategy for the mentioned purpose, as long as the training outliers meet certain quality standards. We hypothesize that the outliers in the OE should possess several characteristics simultaneously to be effective in the adversarial training: diversity, and both conceptual differentiability and analogy to the inliers. These aspects seem to play a more critical role in the adversarial setup compared to the standard training. Next, we propose an adaptive OE method to generate near and diverse outliers by incorporating both text and image domain information. This process helps satisfy the mentioned criteria for the generated outliers and significantly enhances the performance of the OE technique, particularly in adversarial settings. Our method demonstrates its effectiveness across various detection setups, such as novelty detection (ND), Open-Set Recognition (OSR), and out-of-distribution (OOD) detection. Furthermore, we conduct a comprehensive comparison of our approach with other OE techniques in adversarial settings to showcase its effectiveness.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5192