ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in an open-world setting. However, existing OOD detection solutions can be brittle in the open world, facing various types of adversarial OOD inputs. While methods leveraging auxiliary OOD data have emerged, our analysis on illuminative examples reveals a key insight that the majority of auxiliary OOD examples may not meaningfully improve or even hurt the decision boundary of the OOD detector, which is also observed in empirical results on real data. In this paper, we provide a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection. We show that, by mining informative auxiliary OOD data, one can significantly improve OOD detection performance, and somewhat surprisingly, generalize to unseen adversarial attacks. ATOM achieves state-of-the-art performance under a broad family of classic and adversarial OOD evaluation tasks. For example, on the CIFAR-10 in-distribution dataset, ATOM reduces the FPR (at TPR 95%) by up to 57.99% under adversarial OOD inputs, surpassing the previous best baseline by a large margin.
Code (1)
Tasks
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionSimilar Papers 제목 키워드 기반
Informative Outlier Matters: Robustifying Out-of-distribution Detection Using Outlier Mining
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in an open-world setting. However, existing OOD detection solutions can be brittle in the open world, facing various types …
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionRevisiting Energy-Based Model for Out-of-Distribution Detection
Out-of-distribution (OOD) detection is an essential approach to robustifying deep learning models, enabling them to identify inputs that fall outside of their trained distribution. Existing OOD detection methods usually …
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionPOEM: Out-of-Distribution Detection with Posterior Sampling
Out-of-distribution (OOD) detection is indispensable for machine learning models deployed in the open world. Recently, the use of an auxiliary outlier dataset during training (also known as outlier exposure) has shown pr…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionAdversarial Distributions Against Out-of-Distribution Detectors
Out-of-distribution (OOD) detection is the task of determining whether an input lies outside the training data distribution. As an outlier may deviate from the training distribution in unexpected ways, an ideal OOD detec…
Out of Distribution (OOD) DetectionHow Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability
Transformers excel in natural language processing and computer vision tasks. However, they still face challenges in generalizing to Out-of-Distribution (OOD) datasets, i.e. data whose distribution differs from that seen …
Image ClassificationLearning TheoryOut-of-Distribution Detection