paper-with-me

홈 › Papers

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

2026-01-15 · Gerhard Krumpl, Henning Avenhaus, Horst Possegger arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.10836

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Similar Papers 제목 키워드 기반

Some Further Evidence about Magnification and Shape in Neural Gas

2015-03-28 · Giacomo Parigi, Andrea Pedrini, Marco Piastra

Neural gas (NG) is a robust vector quantization algorithm with a well-known mathematical model. According to this, the neural gas samples the underlying data distribution following a power law with a magnification expone…

Quantization

Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?

2026-07-14 · Minh Khoi Ho, Zihao Zhu, Runchuan Zhu, Levina Li 외 arxiv

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While LLMs are trained to …

Decision Making

The Way We Prompt: Conceptual Blending, Neural Dynamics, and Prompt-Induced Transitions in LLMs

2025-05-16 · Makoto Sato

Large language models (LLMs), inspired by neuroscience, exhibit behaviors that often evoke a sense of personality and intelligence-yet the mechanisms behind these effects remain elusive. Here, we operationalize Conceptua…

Prompt Engineering

Metadata Normalization

2021-04-19 · CVPR 2021 1 · Mandy Lu, Qingyu Zhao, Jiequan Zhang, Kilian M. Pohl 외

Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods. While these techniques normalize feature distributions b…

When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains

2026-03-01 · Ahmadreza Jeddi, Kimia Shaban, Negin Baghbanzadeh, Natasha Sharan 외 arxiv

Reinforcement learning (RL) is increasingly used to post-train medical Vision-Language Models (VLMs), yet it remains unclear whether RL improves medical visual reasoning or mainly sharpens behaviors already induced by su…

Reinforcement LearningVisual Reasoning