One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2601.10836v1
• Date: Thu, 15 Jan 2026 20:11:01 GMT
• Title: One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection
• Authors: Gerhard Krumpl, Henning Avenhaus, Horst Possegger,
• Abstract summary: Out-of-distribution (OOD) detection is crucial for deploying robust and reliable machine-learning systems in open-world settings.<n>We benchmark 21 post-hoc, state-of-the-art OOD detection methods across 56 ImageNet-trained models.<n>We observe a strong interdependence between training strategy, detector choice, and resulting OOD performance, indicating that no single method is universally optimal.
• Score: 12.06155749281499
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Out-of-distribution (OOD) detection is crucial for deploying robust and reliable machine-learning systems in open-world settings. Despite steady advances in OOD detectors, their interplay with modern training pipelines that maximize in-distribution (ID) accuracy and generalization remains under-explored. We investigate this link through a comprehensive empirical study. Fixing the architecture to the widely adopted ResNet-50, we benchmark 21 post-hoc, state-of-the-art OOD detection methods across 56 ImageNet-trained models obtained via diverse training strategies and evaluate them on eight OOD test sets. Contrary to the common assumption that higher ID accuracy implies better OOD detection performance, we uncover a non-monotonic relationship: OOD performance initially improves with accuracy but declines once advanced training recipes push accuracy beyond the baseline. Moreover, we observe a strong interdependence between training strategy, detector choice, and resulting OOD performance, indicating that no single method is universally optimal.

Related papers

• Retrieval-Augmented Prompt for OOD Detection [23.092622473716144]
  Out-of-Distribution (OOD) detection is crucial for the reliable deployment of machine learning models in-the-wild.<n>We propose a novel OOD detection method called Retrieval-Augmented Prompt (RAP)<n>RAP augments a pre-trained vision-language model's prompts by retrieving external knowledge, offering enhanced semantic supervision for OOD detection.<n>RAP achieves state-of-the-art performance on large-scale OOD detection benchmarks.
  arXiv  Detail & Related papers  (2025-08-14T11:52:43Z)
• OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary [10.19006278808466]
  Out-of-distribution (OOD) detection remains challenging for deep learning models.<n>We propose OODD, a novel test-time OOD detection method that dynamically maintains and updates an OOD dictionary without fine-tuning.<n>We present an optimized variant of the KNN-based OOD detection framework that achieves a 3x speedup while maintaining detection performance.
  arXiv  Detail & Related papers  (2025-03-13T15:41:56Z)
• The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection [75.65876949930258]
  Out-of-distribution (OOD) detection is essential for model trustworthiness. We show that the superior OOD detection performance of state-of-the-art methods is achieved by secretly sacrificing the OOD generalization ability.
  arXiv  Detail & Related papers  (2024-10-12T07:02:04Z)
• Model-free Test Time Adaptation for Out-Of-Distribution Detection [62.49795078366206]
  We propose a Non-Parametric Test Time textbfAdaptation framework for textbfDistribution textbfDetection (abbr) abbr utilizes online test samples for model adaptation during testing, enhancing adaptability to changing data distributions. We demonstrate the effectiveness of abbr through comprehensive experiments on multiple OOD detection benchmarks.
  arXiv  Detail & Related papers  (2023-11-28T02:00:47Z)
• AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection [79.51071170042972]
  Out-of-distribution (OOD) detection aims to detect test samples that do not fall into any training in-distribution (ID) classes.<n>Data safety and privacy make it infeasible to collect task-specific outliers in advance for different scenarios.<n>We present test-time OOD detection, which allows the deployed model to utilize real OOD data from the unlabeled data stream during testing.
  arXiv  Detail & Related papers  (2023-03-22T02:28:54Z)
• Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need [52.88953913542445]
  We find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD)
  arXiv  Detail & Related papers  (2023-02-06T08:24:41Z)
• Towards Realistic Out-of-Distribution Detection: A Novel Evaluation Framework for Improving Generalization in OOD Detection [14.541761912174799]
  This paper presents a novel evaluation framework for Out-of-Distribution (OOD) detection. It aims to assess the performance of machine learning models in more realistic settings.
  arXiv  Detail & Related papers  (2022-11-20T07:30:15Z)
• ReAct: Out-of-distribution Detection With Rectified Activations [20.792140933660075]
  Out-of-distribution (OOD) detection has received much attention lately due to its practical importance. One of the primary challenges is that models often produce highly confident predictions on OOD data. We propose ReAct--a simple and effective technique for reducing model overconfidence on OOD data.
  arXiv  Detail & Related papers  (2021-11-24T21:02:07Z)
• Provably Robust Detection of Out-of-distribution Data (almost) for free [124.14121487542613]
  Deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OOD) data. In this paper we propose a novel method where from first principles we combine a certifiable OOD detector with a standard classifier into an OOD aware classifier. In this way we achieve the best of two worlds: certifiably adversarially robust OOD detection, even for OOD samples close to the in-distribution, without loss in prediction accuracy and close to state-of-the-art OOD detection performance for non-manipulated OOD data.
  arXiv  Detail & Related papers  (2021-06-08T11:40:49Z)
• ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining [51.19164318924997]
  Adrial Training with informative Outlier Mining improves robustness of OOD detection. ATOM achieves state-of-the-art performance under a broad family of classic and adversarial OOD evaluation tasks.
  arXiv  Detail & Related papers  (2020-06-26T20:58:05Z)
• 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.