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

• URL: http://arxiv.org/abs/2605.28021v1
• Date: Wed, 27 May 2026 06:26:09 GMT
• Title: AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels
• Abstract summary: Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios.<n>We propose underlineAdaptive Confidence underlineOE (AOE), a simple yet effective method that leverages temperature scaling to recalibrate outlier labels.
• Score: 7.13211812738884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 \underline{A}daptive Confidence \underline{OE} (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.

Related papers

• Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptation [52.620992698137236]
  Open-set test-time adaptation (OSTTA) addresses the challenge of adapting models to new environments.<n>In this paper, we first analyze the limitations of entropy in OSTTA and then introduce an angular loss to regulate feature norm magnitudes.<n>Our method achieves strong OOD detection while maintaining high ID classification performance.
  arXiv  Detail & Related papers  (2026-04-02T04:00:57Z)
• Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detection [62.1052001316508]
  Semantically coherent out-of-distribution detection (SCOOD) is a recently proposed realistic OOD detection setting.<n>We propose a concise SCOOD framework based on predictive sample assignment (PSA)<n>Our approach outperforms the state-of-the-art methods by a significant margin.
  arXiv  Detail & Related papers  (2025-12-15T01:18:38Z)
• AdaSCALE: Adaptive Scaling for OOD Detection [1.6921396880325779]
  Out-of-distribution (OOD) detection methods leverage activation shaping to improve the separation between in-distribution (ID) and OOD inputs.<n>We propose textbfAdaSCALE, an adaptive scaling procedure that dynamically adjusts the percentile threshold based on a sample's estimated OOD likelihood.<n>Our approach achieves state-of-the-art OOD detection performance, outperforming the latest rival OptFS by 14.94% in near-OOD and 21.67% in far-OOD in average FPR@95 metric on the ImageNet-1k benchmark.
  arXiv  Detail & Related papers  (2025-03-11T04:10:06Z)
• Going Beyond Conventional OOD Detection [0.0]
  Out-of-distribution (OOD) detection is critical to ensure the safe deployment of deep learning models in critical applications.<n>We present a unified Approach to Spurimatious, fine-grained, and Conventional OOD Detection (ASCOOD)<n>Our approach effectively mitigates the impact of spurious correlations and encourages capturing fine-grained attributes.
  arXiv  Detail & Related papers  (2024-11-16T13:04:52Z)
• Margin-bounded Confidence Scores for Out-of-Distribution Detection [2.373572816573706]
  We propose a novel method called Margin bounded Confidence Scores (MaCS) to address the nontrivial OOD detection problem. MaCS enlarges the disparity between ID and OOD scores, which in turn makes the decision boundary more compact. Experiments on various benchmark datasets for image classification tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-09-22T05:40:25Z)
• Distilling the Unknown to Unveil Certainty [66.29929319664167]
  Out-of-distribution (OOD) detection is critical for identifying test samples that deviate from in-distribution (ID) data, ensuring network robustness and reliability.<n>This paper presents a flexible framework for OOD knowledge distillation that extracts OOD-sensitive information from a network to develop a binary classifier capable of distinguishing between ID and OOD samples.
  arXiv  Detail & Related papers  (2023-11-14T08:05:02Z)
• Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation [110.34982764201689]
  Out-of-distribution (OOD) detection is important for deploying reliable machine learning models on real-world applications. Recent advances in outlier exposure have shown promising results on OOD detection via fine-tuning model with informatively sampled auxiliary outliers. We propose a novel framework, namely, Diversified Outlier Exposure (DivOE), for effective OOD detection via informative extrapolation based on the given auxiliary outliers.
  arXiv  Detail & Related papers  (2023-10-21T07:16:09Z)
• Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors [39.8194799829348]
  We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors. Motivated by the difficulty of curating suitable calibration datasets, synthetic augmentations have become highly prevalent for inlier/outlier specification. We find that the optimal protocol is to synthesize latent-space inliers along with diverse pixel-space outliers.
  arXiv  Detail & Related papers  (2022-07-12T03:42:05Z)
• Out of Distribution Detection via Neural Network Anchoring [38.36467447555689]
  We exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection. We propose a new training strategy called anchoring that can estimate appropriate temperature values for each sample. In contrast to some of the best-performing OOD detection approaches, our method does not require exposure to additional outlier datasets.
  arXiv  Detail & Related papers  (2022-07-08T21:01:09Z)
• Self-Supervised Anomaly Detection by Self-Distillation and Negative Sampling [1.304892050913381]
  We show that self-distillation of the in-distribution training set together with contrasting against negative examples strongly improves OOD detection. We observe that by leveraging negative samples, which keep the statistics of low-level features while changing the high-level semantics, higher average detection performance is obtained.
  arXiv  Detail & Related papers  (2022-01-17T12:33:14Z)
• Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection [72.35532598131176]
  We propose an unsupervised method to detect OOD samples using a $k$-NN density estimate. We leverage a recent insight about label smoothing, which we call the emphLabel Smoothed Embedding Hypothesis We show that our proposal outperforms many OOD baselines and also provide new finite-sample high-probability statistical results.
  arXiv  Detail & Related papers  (2021-02-09T21:04:44Z)
• Robust Out-of-distribution Detection for Neural Networks [51.19164318924997]
  We show that existing detection mechanisms can be extremely brittle when evaluating on in-distribution and OOD inputs. We propose an effective algorithm called ALOE, which performs robust training by exposing the model to both adversarially crafted inlier and outlier examples.
  arXiv  Detail & Related papers  (2020-03-21T17:46:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.