Exploiting Local Flatness for Efficient Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2606.29952v1
• Date: Mon, 29 Jun 2026 08:27:27 GMT
• Title: Exploiting Local Flatness for Efficient Out-of-Distribution Detection
• Abstract summary: Out-of-distribution (OOD) data is crucial for reliable machine learning deployment.<n>We propose Fold, a lightweight flatness-modulated OOD detector.<n>We show that Fold outperforms prior methods, improving the average AUROC by 1.63% and reducing FPR95 by 2.30%.
• Score: 6.307330944209518
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting out-of-distribution (OOD) data is crucial for reliable machine learning deployment. Among detection strategies, post-hoc methods are particularly attractive due to their efficiency, as they operate directly on pre-trained networks without requiring retraining. Within this paradigm, one promising direction exploits loss-landscape curvature to estimate model uncertainty; however, such methods incur substantial computational cost and rely on implicit assumptions about how landscape flatness differs between in-distribution (ID) and OOD data. In this work, we provide the first systematic investigation of this curvature discrepancy and show that OOD inputs exhibit larger Hessian curvature than ID data, with the gap widening under stronger distributional shifts. Motivated by these observations, we propose Fold, a lightweight flatness-modulated OOD detector that leverages the feature Hessian and partial feature normalization to improve ID-OOD separability while avoiding costly parameter-space curvature approximations. To optimally adapt this normalization across diverse datasets, we further introduce AutoFold, a self-supervised tuning scheme that synthesizes pseudo-OOD samples via ID logit masking for automatic calibration without requiring external data. Experiments on OOD benchmarks show that Fold outperforms prior methods, improving the average AUROC by 1.63% and reducing FPR95 by 2.30%, while maintaining computational efficiency comparable to a standard forward pass. Supported by theoretical analysis and extensive ablations, Fold provides a principled and practical solution for robust real-world deployment.

Related papers

• Revisiting Logit Distributions for Reliable Out-of-Distribution Detection [73.9121001113687]
  Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications.<n>LogitGap is a novel post-hoc OOD detection method that exploits the relationship between the maximum logit and the remaining logits.<n>We show that LogitGap consistently achieves state-of-the-art performance across diverse OOD detection scenarios and benchmarks.
  arXiv  Detail & Related papers  (2025-10-23T02:16:45Z)
• 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)
• Feed Two Birds with One Scone: Exploiting Function-Space Regularization for Both OOD Robustness and ID Fine-Tuning Performance [72.57668440744301]
  We propose a novel regularization that constrains the distance of fine-tuning and pre-trained model in the function space with simulated OOD samples.<n>Our approach could consistently improve both downstream task ID fine-tuning performance and OOD robustness across a variety of CLIP backbones.
  arXiv  Detail & Related papers  (2025-08-31T12:14:34Z)
• Distributionally Robust Optimization with Adversarial Data Contamination [49.89480853499918]
  We focus on optimizing Wasserstein-1 DRO objectives for generalized linear models with convex Lipschitz loss functions.<n>Our primary contribution lies in a novel modeling framework that integrates robustness against training data contamination with robustness against distributional shifts.<n>This work establishes the first rigorous guarantees, supported by efficient computation, for learning under the dual challenges of data contamination and distributional shifts.
  arXiv  Detail & Related papers  (2025-07-14T18:34:10Z)
• Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection [14.833454650943805]
  hierarchical variational autoencoders (HVAEs) offer improved representational capacity over traditional VAEs.<n>Existing approaches often allocate latent capacity arbitrarily, leading to ineffective representations or posterior collapse.<n>We introduce a theoretically grounded framework for optimizing latent dimension allocation in HVAEs.<n>We prove the existence of an optimal allocation ratio $rast$ under a fixed latent budget, and empirically show that tuning this ratio consistently improves OOD detection performance.
  arXiv  Detail & Related papers  (2025-06-11T18:16:19Z)
• Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning [73.40364018029673]
  Continual test-time adaptive object detection (CTTA-OD) aims to online adapt a source pre-trained detector to ever-changing environments.<n>Our motivation stems from the observation that not all learned source features are beneficial.<n>Our method achieves superior adaptation performance while reducing computational overhead by 12% in FLOPs.
  arXiv  Detail & Related papers  (2025-06-03T05:27:56Z)
• Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection [15.184096796229115]
  We propose a post-hoc method, Perturbation-Rectified OOD detection (PRO), based on the insight that prediction confidence for OOD inputs is more susceptible to reduction under perturbation than in-distribution (IND) inputs.<n>On a CIFAR-10 model with adversarial training, PRO effectively detects near-OOD inputs, achieving a reduction of more than 10% on FPR@95 compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-24T15:32:33Z)
• 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)
• Towards Calibrated Robust Fine-Tuning of Vision-Language Models [97.19901765814431]
  This work proposes a robust fine-tuning method that improves both OOD accuracy and confidence calibration simultaneously in vision language models. We show that both OOD classification and OOD calibration errors have a shared upper bound consisting of two terms of ID data. Based on this insight, we design a novel framework that conducts fine-tuning with a constrained multimodal contrastive loss enforcing a larger smallest singular value.
  arXiv  Detail & Related papers  (2023-11-03T05:41:25Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection [12.341250124228859]
  We propose a simple yet effective generalized OOD detection method independent of out-of-distribution datasets. Our approach relies on self-supervised feature learning of the training samples, where the embeddings lie on a compact low-dimensional space. We empirically show that a pre-trained model with self-supervised contrastive learning yields a better model for uni-dimensional feature learning in the latent space.
  arXiv  Detail & Related papers  (2022-04-06T03:05:58Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)

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.