Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning

• URL: http://arxiv.org/abs/2605.05638v1
• Date: Thu, 07 May 2026 03:45:52 GMT
• Title: Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
• Abstract summary: We show that modern pretrained models encode sufficient geometric structure for accurate label-free out-of-distribution detection.<n>Our results suggest that label-free OOD detection depends strongly on the geometry exposed by frozen pretrained backbones.
• Score: 5.008779702997125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Models trained with deep learning often fail to signal when inputs fall outside their training data manifold, leading to unreliable predictions under distribution shift. Prior work suggests that effective out-of-distribution (OOD) detection often requires class-conditional modeling or specialized models obtained through supervised fine-tuning. We revisit this assumption in modern pretrained models and show that their frozen representations already encode sufficient geometric structure for accurate label-free OOD detection. Across 59 backbone-task pairings spanning vision and language, we compare two complementary label-free detectors: a global Mahalanobis estimator fit on unlabeled latent representations, and ReSCOPED, a lightweight, diffusion-based typicality estimator operating on the same features at a local level. Despite their different detection mechanisms, representation scaling reveals a consistent regime-dependent pattern: both local and global detectors' absolute performance improves with better representation quality, and performance gaps between the two detectors disappear across both language and vision tasks as representations scale. These results suggest that label-free OOD detection depends strongly on the geometry exposed by frozen pretrained backbones, reducing the importance of detector choice as backbone scale increases and enabling efficient deployment directly on frozen models.

Related papers

• AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors [11.468095590140777]
  AEGIS is a semantic aware and uncertainty guided adversarial detection framework for vision sensors pipelines.<n>A SemantiGAN module functions as a multi class semantic discriminator, identifying and filtering visually inconsistent adversarial inputs.<n> Evaluations on the Tiny ImageNet dataset demonstrate the effectiveness of AEGIS.
  arXiv  Detail & Related papers  (2026-06-25T12:03:02Z)
• Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection [51.93878677594561]
  In unsupervised graph-level OOD detection, models are typically trained using only in-distribution (ID) data.<n>We propose a Policy-Guided Outlier Synthesis framework that replaces statics with a learned exploration strategy.
  arXiv  Detail & Related papers  (2026-02-28T11:40:18Z)
• Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models [59.242742594156546]
  CoEvo is a test-time framework that performs bidirectional, sample-conditioned adaptation of both textual and visual proxies.<n>CoEvo achieves state-of-the-art performance, improving AUROC by 1.33% and reducing FPR95 by 45.98% on ImageNet-1K compared to strong negative-label baselines.
  arXiv  Detail & Related papers  (2026-01-13T12:08:26Z)
• AgentIAD: Tool-Augmented Single-Agent for Industrial Anomaly Detection [9.208080780536504]
  AgentIAD is a tool-driven framework that enables multi-stage visual inspection.<n>AgentIAD achieves a new state-of-the-art 97.62% classification accuracy on MMAD.
  arXiv  Detail & Related papers  (2025-12-15T18:57:04Z)
• Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries [15.43092254877282]
  Key challenge in graph out-of-distribution (OOD) detection lies in the absence of ground-truth OOD samples during training.<n>We propose a novel test-time graph OOD detection method, termed BaCa, that calibrates OOD scores using dual dynamically updated dictionaries.<n>BaCa significantly outperforms existing state-of-the-art methods in OOD detection.
  arXiv  Detail & Related papers  (2025-11-17T16:14:48Z)
• Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories [6.634696833862699]
  We introduce DISC: Diffusion-based Statistical characterization.<n> DISC captures statistical discrepancies across multiple noise levels.<n>It matches or surpasses state-of-the-art detectors for OOD detection and, crucially, also classifies OOD type.
  arXiv  Detail & Related papers  (2025-10-20T10:18:45Z)
• SCOPED: Score-Curvature Out-of-distribution Proximity Evaluator for Diffusion [5.008779702997125]
  Out-of-distribution (OOD) detection is essential for reliable deployment of machine learning systems in vision, robotics, reinforcement learning, and beyond.<n>We introduce Score-Curvature Out-of-distribution Proximity Evaluator for Diffusion (SCOPED)<n>SCOPED is computed from a single diffusion model trained once on a diverse dataset, and combines the Jacobian trace and squared norm of the model's score function into a single test statistic.<n>On four vision benchmarks, SCOPED achieves competitive or state-of-the-art precision-recall scores despite its low computational cost.
  arXiv  Detail & Related papers  (2025-10-01T20:54:49Z)
• From Global to Local: Multi-scale Out-of-distribution Detection [129.37607313927458]
  Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection. We propose Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details.
  arXiv  Detail & Related papers  (2023-08-20T11:56:25Z)
• Watermarking for Out-of-distribution Detection [76.20630986010114]
  Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models. We propose a general methodology named watermarking in this paper. We learn a unified pattern that is superimposed onto features of original data, and the model's detection capability is largely boosted after watermarking.
  arXiv  Detail & Related papers  (2022-10-27T06:12:32Z)
• Tracking the risk of a deployed model and detecting harmful distribution shifts [105.27463615756733]
  In practice, it may make sense to ignore benign shifts, under which the performance of a deployed model does not degrade substantially. We argue that a sensible method for firing off a warning has to both (a) detect harmful shifts while ignoring benign ones, and (b) allow continuous monitoring of model performance without increasing the false alarm rate.
  arXiv  Detail & Related papers  (2021-10-12T17:21:41Z)
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders [51.691585766702744]
  We propose a variant of Adversarial Autoencoder which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction. We put forward an alternative measure of anomaly score to replace the reconstruction-based metric. Our method outperforms the current state-of-the-art methods for anomaly detection on several OOD detection benchmarks.
  arXiv  Detail & Related papers  (2020-03-24T08:26:58Z)

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.