Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistency

• URL: http://arxiv.org/abs/2608.11541v1
• Date: Wed, 12 Aug 2026 01:13:33 GMT
• Title: Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistency
• Abstract summary: Robust Ambiguity Detection (RAD) framework is advanced for quantifying predictive ambiguity using two complementary metrics.<n>RAD is evaluated on synthetic datasets with systematically controlled overlap, as well as several real-world datasets.
• Score: 6.07595146080737
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning models should be robust, in the sense of remaining predictively consistent under permissible variations. A model's predictions should ideally remain unchanged when it is replaced by a functionally equivalent one, or when its inputs are subject to minor, admissible perturbations. If such changes alter a prediction significantly, then the prediction is "ambiguous" with respect to the model. Models should abstain from making such ambiguous predictions and/or should flag them for human inspection, especially in high-stakes decision-making scenarios. However, in practice, such ambiguity is not easy to identify once a model is deployed. Here, the Robust Ambiguity Detection (RAD) framework is advanced for quantifying predictive ambiguity using two complementary metrics: Model-Space Consistency and Feature-Space Consistency. These two scores, the RAD Score-Pair, visualised through the RAD Plot, provide an interpretable characterisation of the sources of ambiguity and the actions a user may consider in response. RAD is evaluated on synthetic datasets with systematically controlled overlap, as well as several real-world datasets where the level of ambiguity cannot be directly inspected. Finally, we demonstrate a downstream application of RAD where samples are ranked by their RAD Pareto-Rank and the most ambiguous are abstained from prediction, achieving performance comparable to existing rejection-based approaches.

Related papers

• Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning [5.008779702997125]
  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.
  arXiv  Detail & Related papers  (2026-05-07T03:45:52Z)
• Uncertainty-Aware Trajectory Prediction: A Unified Framework Harnessing Positional and Semantic Uncertainties [18.530958966955847]
  Trajectory prediction seeks to forecast the future motion of dynamic entities, such as vehicles and pedestrians, given a temporal horizon of historical movement data.<n>A central challenge in this domain is the inherent uncertainty in real-time maps, arising from two primary sources.<n>We propose a novel unified framework that jointly models positional and semantic uncertainties and explicitly integrates them into the trajectory prediction pipeline.
  arXiv  Detail & Related papers  (2026-03-31T07:35:55Z)
• DANCE: Doubly Adaptive Neighborhood Conformal Estimation [12.643121779828526]
  We propose a doubly locally adaptive nearest-neighbor based conformal algorithm combining two novel nonconformity scores directly using the data's embedded representation.<n>We test against state-of-the-art local, task-adapted and zero-shot conformal baselines, demonstrating DANCE's superior blend of set size efficiency and robustness across various datasets.
  arXiv  Detail & Related papers  (2026-02-24T07:54:53Z)
• DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment [92.70019102733453]
  Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence.<n>We propose DistDF, which achieves alignment by alternatively minimizing a discrepancy between the conditional forecast and label distributions.
  arXiv  Detail & Related papers  (2025-10-28T16:09:59Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Operational range bounding of spectroscopy models with anomaly detection [0.0]
  Isolation Forests are shown to effectively identify contexts where prediction models are likely to fail. Best performance is seen when Isolation Forests model projections of the prediction model's explainability SHAP values.
  arXiv  Detail & Related papers  (2024-08-05T15:59:36Z)
• Onboard Out-of-Calibration Detection of Deep Learning Models using Conformal Prediction [4.856998175951948]
  We show that conformal prediction algorithms are related to the uncertainty of the deep learning model and that this relation can be used to detect if the deep learning model is out-of-calibration. An out-of-calibration detection procedure relating the model uncertainty and the average size of the conformal prediction set is presented.
  arXiv  Detail & Related papers  (2024-05-04T11:05:52Z)
• Source-Free Unsupervised Domain Adaptation with Hypothesis Consolidation of Prediction Rationale [53.152460508207184]
  Source-Free Unsupervised Domain Adaptation (SFUDA) is a challenging task where a model needs to be adapted to a new domain without access to target domain labels or source domain data. This paper proposes a novel approach that considers multiple prediction hypotheses for each sample and investigates the rationale behind each hypothesis. To achieve the optimal performance, we propose a three-step adaptation process: model pre-adaptation, hypothesis consolidation, and semi-supervised learning.
  arXiv  Detail & Related papers  (2024-02-02T05:53:22Z)
• Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive? [93.10694819127608]
  We propose a unified evaluation pipeline for forecasting methods with real-world perception inputs. Our in-depth study uncovers a substantial performance gap when transitioning from curated to perception-based data.
  arXiv  Detail & Related papers  (2023-06-15T17:03:14Z)
• Sharing pattern submodels for prediction with missing values [12.981974894538668]
  Missing values are unavoidable in many applications of machine learning and present challenges both during training and at test time. We propose an alternative approach, called sharing pattern submodels, which i) makes predictions robust to missing values at test time, ii) maintains or improves the predictive power of pattern submodels andiii) has a short description, enabling improved interpretability.
  arXiv  Detail & Related papers  (2022-06-22T15:09:40Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• Multivariate Probabilistic Regression with Natural Gradient Boosting [63.58097881421937]
  We propose a Natural Gradient Boosting (NGBoost) approach based on nonparametrically modeling the conditional parameters of the multivariate predictive distribution. Our method is robust, works out-of-the-box without extensive tuning, is modular with respect to the assumed target distribution, and performs competitively in comparison to existing approaches.
  arXiv  Detail & Related papers  (2021-06-07T17:44:49Z)

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.