# ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining

arXiv: https://arxiv.org/abs/2006.15207 · HTML: https://mlsanity.com/paper/2006.15207/

## Key facts

- Cited by 116 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

## Built on by (most cited first, 30 of 116)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [On the Importance of Gradients for Detecting Distributional Shifts in the Wild](https://mlsanity.com/paper/2110.00218/) (2021)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space](https://mlsanity.com/paper/2105.01879/) (2021)
- [Delving into Out-of-Distribution Detection with Vision-Language Representations](https://mlsanity.com/paper/2211.13445/) (2022)
- [DICE: Leveraging Sparsification for Out-of-Distribution Detection](https://mlsanity.com/paper/2111.09805/) (2021)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [Is Out-of-Distribution Detection Learnable?](https://mlsanity.com/paper/2210.14707/) (2022)
- [POEM: Out-of-Distribution Detection with Posterior Sampling](https://mlsanity.com/paper/2206.13687/) (2022)
- [Can multi-label classification networks know what they don't know?](https://mlsanity.com/paper/2109.14162/) (2021)
- [Training OOD Detectors in their Natural Habitats](https://mlsanity.com/paper/2202.03299/) (2022)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Provable Guarantees for Understanding Out-of-distribution Detection](https://mlsanity.com/paper/2112.00787/) (2021)
- [Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments](https://mlsanity.com/paper/2106.03917/) (2021)
- [Boosting Out-of-distribution Detection with Typical Features](https://mlsanity.com/paper/2210.04200/) (2022)
- [Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition](https://mlsanity.com/paper/2207.01160/) (2022)
- [Out-of-distribution Detection with Implicit Outlier Transformation](https://mlsanity.com/paper/2303.05033/) (2023)
- [ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection](https://mlsanity.com/paper/2311.15243/) (2023)
- [Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation](https://mlsanity.com/paper/2310.13923/) (2023)
- [Learning to Augment Distributions for Out-of-Distribution Detection](https://mlsanity.com/paper/2311.01796/) (2023)
- [Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources](https://mlsanity.com/paper/2311.03236/) (2023)
- [Block Selection Method for Using Feature Norm in Out-of-distribution Detection](https://mlsanity.com/paper/2212.02295/) (2022)
- [Provably Bounding Neural Network Preimages](https://mlsanity.com/paper/2302.01404/) (2023)
- [Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2306.02879/) (2023)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection](https://mlsanity.com/paper/2402.17888/) (2024)
- [GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients](https://mlsanity.com/paper/2308.00310/) (2023)
- [Provably Robust Detection of Out-of-distribution Data (almost) for free](https://mlsanity.com/paper/2106.04260/) (2021)
- [OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary](https://mlsanity.com/paper/2503.10468/) (2025)

## Abstract (arXiv)

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.