# AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels

arXiv: https://arxiv.org/abs/2605.28021 · HTML: https://mlsanity.com/paper/2605.28021/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [ReAct: Out-of-distribution Detection With Rectified Activations](https://mlsanity.com/paper/2111.12797/) (2021)
- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [DenseNet Models for Tiny ImageNet Classification](https://mlsanity.com/paper/1904.10429/) (2019)
- [DOS: Diverse Outlier Sampling for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.02031/) (2023)
- [Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability](https://mlsanity.com/paper/2306.03715/) (2023)
- [How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?](https://mlsanity.com/paper/2312.14452/) (2023)
- [T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning](https://mlsanity.com/paper/2503.22163/) (2025)
- [Generalizing GradCAM for Embedding Networks](https://mlsanity.com/paper/2402.00909/) (2024)

## Abstract (arXiv)

Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknown samples can lead to unreliable decisions. Outlier Exposure (OE) has emerged as a promising OOD detection paradigm by introducing auxiliary outliers during training to enlarge the margin between in-distribution (ID) and OOD samples. Existing OE-based methods typically enlarge this margin by employing uniform labels to maximize the entropy of OOD samples over ID categories. However, we theoretically show that uniform labels inevitably disregard the relations between OOD samples and ID categories, termed the over-softening effect, leading to a suboptimal margin bound. Our theoretical analysis further reveals that explicitly exploiting such relations can instead yield improved OOD detection performance. Motivated by this insight, we propose underlineAdaptive Confidence underlineOE (AOE), a simple yet effective method that leverages temperature scaling to recalibrate outlier labels. Specifically, AOE generates adaptive soft targets from temperature-scaled model predictions for OOD samples, where the learnable temperature smooths the prediction distribution without fully erasing class-wise relational information. By supervising OOD samples with these adaptive soft targets, AOE preserves the semantic proximity between OOD samples and ID categories while encouraging the softened targets to approach a high-entropy distribution, thereby suppressing overconfident OOD predictions and enlarging the separation margin. Extensive experiments across diverse benchmarks demonstrate the effectiveness of AOE.