Robustness and uncertainty: two complementary aspects of the reliability of the predictions of a classifier

• URL: http://arxiv.org/abs/2512.15492v1
• Date: Wed, 17 Dec 2025 14:40:14 GMT
• Title: Robustness and uncertainty: two complementary aspects of the reliability of the predictions of a classifier
• Abstract summary: We consider two approaches for assessing the reliability of individual predictions of a classifier: Robustness Quantification (RQ) and Uncertainty Quantification (UQ)<n>We compare both approaches on a number of benchmark datasets and show that there is no clear winner between the two, but that they are complementary and can be combined to obtain a hybrid approach that outperforms both RQ and UQ.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider two conceptually different approaches for assessing the reliability of the individual predictions of a classifier: Robustness Quantification (RQ) and Uncertainty Quantification (UQ). We compare both approaches on a number of benchmark datasets and show that there is no clear winner between the two, but that they are complementary and can be combined to obtain a hybrid approach that outperforms both RQ and UQ. As a byproduct of our approach, for each dataset, we also obtain an assessment of the relative importance of uncertainty and robustness as sources of unreliability.

Related papers

• It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spaces [23.472868138533926]
  Uncertainty Quantification (UQ) plays a vital role in enhancing the reliability of deep learning model predictions.<n>This paper addresses the dual nature of uncertainty, focusing on their joint integration in high-dimensional regression tasks.<n>We propose a novel approach that approximates the resulting joint uncertainty using a low-rank plus diagonal covariance structure.
  arXiv  Detail & Related papers  (2026-08-25T13:08:17Z)
• Robustness Quantification and Uncertainty Quantification: Comparing Two Methods for Assessing the Reliability of Classifier Predictions [0.0]
  We consider two approaches for assessing the reliability of individual predictions of a classifier: Robustness Quantification (RQ) and Uncertainty Quantification (UQ)<n>We show that RQ is capable of outperforming UQ, both in a standard setting and in the presence of distribution shift.<n>We also demonstrate the complementarity of RQ and UQ by showing that a combination of both approaches can lead to even better reliability assessments.
  arXiv  Detail & Related papers  (2026-03-24T09:31:13Z)
• Uncertainty-Supervised Interpretable and Robust Evidential Segmentation [16.64288013782432]
  Uncertainty estimation has been widely studied in medical image segmentation as a tool to provide reliability.<n>Previous methods generally lack effective supervision in uncertainty estimation.<n>We propose a self-supervised approach to guide the learning of uncertainty.
  arXiv  Detail & Related papers  (2025-09-21T14:31:47Z)
• A Context-Aware Dual-Metric Framework for Confidence Estimation in Large Language Models [6.62851757612838]
  Current confidence estimation methods for large language models (LLMs) neglect the relevance between responses and contextual information.<n>We propose CRUX, which integrates context faithfulness and consistency for confidence estimation via two novel metrics.<n> Experiments across three benchmark datasets demonstrate CRUX's effectiveness, achieving the highest AUROC than existing baselines.
  arXiv  Detail & Related papers  (2025-08-01T12:58:34Z)
• SConU: Selective Conformal Uncertainty in Large Language Models [59.25881667640868]
  We propose a novel approach termed Selective Conformal Uncertainty (SConU)<n>We develop two conformal p-values that are instrumental in determining whether a given sample deviates from the uncertainty distribution of the calibration set at a specific manageable risk level.<n>Our approach not only facilitates rigorous management of miscoverage rates across both single-domain and interdisciplinary contexts, but also enhances the efficiency of predictions.
  arXiv  Detail & Related papers  (2025-04-19T03:01:45Z)
• Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching [61.73532883992135]
  We propose a new uncertainty-aware stereo matching framework.<n>We adopt Bayes risk as the measurement of uncertainty and use it to separately estimate data and model uncertainty.
  arXiv  Detail & Related papers  (2024-12-24T23:28:20Z)
• Label-Confidence-Aware Uncertainty Estimation in Natural Language Generation [8.635811152610604]
  Uncertainty Quantification (UQ) is crucial for ensuring the safety and robustness of AI systems.<n>We propose a label-confidence-aware (LCA) uncertainty estimation based on Kullback-Leibler divergence bridging between samples and label source.
  arXiv  Detail & Related papers  (2024-12-10T07:35:23Z)
• Quantification of Predictive Uncertainty via Inference-Time Sampling [57.749601811982096]
  We propose a post-hoc sampling strategy for estimating predictive uncertainty accounting for data ambiguity. The method can generate different plausible outputs for a given input and does not assume parametric forms of predictive distributions.
  arXiv  Detail & Related papers  (2023-08-03T12:43:21Z)
• Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval [51.83967175585896]
  UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously. Data uncertainty captures the noise" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction.
  arXiv  Detail & Related papers  (2022-10-24T17:53:20Z)
• Trusted Multi-View Classification with Dynamic Evidential Fusion [73.35990456162745]
  We propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC) TMC provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.
  arXiv  Detail & Related papers  (2022-04-25T03:48:49Z)
• Deep Classifiers with Label Noise Modeling and Distance Awareness [27.47689966724718]
  We propose the HetSNGP method for jointly modeling the model and data uncertainty. We show that our proposed model affords a favorable combination between these two complementary types of uncertainty. We also propose HetSNGP Ensemble, an ensembled version of our method which adds an additional type of uncertainty.
  arXiv  Detail & Related papers  (2021-10-06T09:29:12Z)
• Ensemble-based Uncertainty Quantification: Bayesian versus Credal Inference [0.0]
  We consider ensemble-based approaches to uncertainty quantification. We specifically focus on Bayesian methods and approaches based on so-called credal sets. The effectiveness of corresponding measures is evaluated and compared in an empirical study on classification with a reject option.
  arXiv  Detail & Related papers  (2021-07-21T22:47:24Z)
• Trusted Multi-View Classification [76.73585034192894]
  We propose a novel multi-view classification method, termed trusted multi-view classification. It provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed algorithm jointly utilizes multiple views to promote both classification reliability and robustness.
  arXiv  Detail & Related papers  (2021-02-03T13:30:26Z)

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.