Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts

• URL: http://arxiv.org/abs/2512.08445v1
• Date: Tue, 09 Dec 2025 10:19:07 GMT
• Title: Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts
• Abstract summary: Subset selection-based methods are widely used to explain deep vision models.<n>We introduce a framework that combines submodular subset selection with layer-wise, gradient-based uncertainty estimation.<n>Our approach estimates uncertainty via adaptive weight perturbations and uses these estimates to guide submodular optimization.
• Score: 15.077604091703797
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in in-distribution (ID) settings, their behavior under out-of-distribution (OOD) conditions remains poorly understood. Through extensive experiments across multiple ID-OOD sets, we find that reliability of the existing subset based methods degrades markedly, yielding redundant, unstable, and uncertainty-sensitive explanations. To address these shortcomings, we introduce a framework that combines submodular subset selection with layer-wise, gradient-based uncertainty estimation to improve robustness and fidelity without requiring additional training or auxiliary models. Our approach estimates uncertainty via adaptive weight perturbations and uses these estimates to guide submodular optimization, ensuring diverse and informative subset selection. Empirical evaluations show that, beyond mitigating the weaknesses of existing methods under OOD scenarios, our framework also yields improvements in ID settings. These findings highlight limitations of current subset-based approaches and demonstrate how uncertainty-driven optimization can enhance attribution and object-level interpretability, paving the way for more transparent and trustworthy AI in real-world vision applications.

Related papers

• Interpretable Uncertainty for Adaptive Retrieval and Reasoning in Question Answering [11.42036728689981]
  Large language models (LLMs) achieve a strong performance in question answering (QA), but remain prone to hallucinations and suffer from limited transparency.<n>We propose an uncertainty-aware framework for adaptive QA based on explicit signals derived from LLM internal representations.
  arXiv  Detail & Related papers  (2026-07-08T13:12:39Z)
• Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
  We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
  arXiv  Detail & Related papers  (2026-05-06T13:08:12Z)
• A Bayesian Framework for Uncertainty-Aware Explanations in Power Quality Disturbance Classification [3.68407754316989]
  This paper proposes a Bayesian explanation framework that models explanation uncertainty by generating a relevance attribution distribution for each instance.<n>It allows experts to select explanations based on confidence percentiles, thereby tailoring interpretability according to specific disturbance types.<n>Experiments on synthetic and real-world power quality datasets demonstrate that the proposed framework improves the transparency and reliability of PQD classifiers.
  arXiv  Detail & Related papers  (2026-04-15T09:22:47Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Robust Uncertainty Estimation under Distribution Shift via Difference Reconstruction [2.920726125254978]
  Estimating uncertainty in deep learning models is critical for reliable decision-making in high-stakes applications such as medical imaging.<n>Prior research has established that the difference between an input sample and its reconstructed version can serve as a useful proxy for uncertainty.<n>We propose Difference Reconstruction Uncertainty Estimation (DRUE), a method that mitigates this limitation by reconstructing inputs from two intermediate layers and measuring the discrepancy between their outputs as the uncertainty score.
  arXiv  Detail & Related papers  (2026-01-27T08:23:00Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction [51.50282796099369]
  This paper develops a multi-dimensional instruction uncertainty reduction framework to generate semantically constrained adversarial examples.<n>By predicting the language-guided sampling process, the optimization process will be stabilized by the designed ResAdv-DDIM sampler.<n>We realize the reference-free generation of semantically constrained 3D adversarial examples for the first time.
  arXiv  Detail & Related papers  (2025-10-27T04:02:52Z)
• DEFNet: Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment [5.517243185525322]
  Blind image quality assessment (BIQA) methods often incorporate auxiliary tasks to improve performance.<n>We propose a multitasks-based Deep Evidential Fusion Network (DEFNet) for BIQA, which performs multitask optimization with the assistance of scene and distortion type classification tasks.
  arXiv  Detail & Related papers  (2025-07-25T16:36:45Z)
• Extending Epistemic Uncertainty Beyond Parameters Would Assist in Designing Reliable LLMs [40.7342896954488]
  We advocate for the adoption of a framework that provides a coherent foundation to reason about uncertainty and clarify the reducibility of uncertainty.<n>By supporting active resolution rather than passive avoidance, it opens the door to more reliable, transparent, and broadly applicable LLM systems.
  arXiv  Detail & Related papers  (2025-06-09T05:52:03Z)
• Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer [55.66973223528494]
  We develop a Bayesian Non-negative Decision Layer (BNDL), which reformulates deep neural networks as a conditional Bayesian non-negative factor analysis.<n>BNDL can model complex dependencies and provide robust uncertainty estimation.<n>We also offer theoretical guarantees that BNDL can achieve effective disentangled learning.
  arXiv  Detail & Related papers  (2025-05-28T10:23:34Z)
• Epistemic Uncertainty-aware Recommendation Systems via Bayesian Deep Ensemble Learning [2.3310092106321365]
  We propose an ensemble-based supermodel to generate more robust and reliable predictions.<n>We also introduce a new interpretable non-linear matching approach for the user and item embeddings.
  arXiv  Detail & Related papers  (2025-04-14T23:04:35Z)
• Uncertainty Guided Refinement for Fine-Grained Salient Object Detection [35.6505339733396]
  We introduce the uncertainty guidance learning approach to salient object detection (SOD)<n>We design a novel Uncertainty Guided Refinement Attention Network (UGRAN)<n> Experiments on seven benchmark datasets demonstrate the superiority of the proposed UGRAN over the state-of-the-art methodologies.
  arXiv  Detail & Related papers  (2025-04-13T17:34:37Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)
• Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
  empowerment principle enables unsupervised stabilization of dynamical systems at upright positions. We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel. We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
  arXiv  Detail & Related papers  (2020-07-14T21:10:16Z)
• Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning [17.10036674236381]
  Wrong predictions for out-of-distribution data can cause safety critical situations in machine learning systems. We propose a framework for uncertainty-based OOD classification: UBOOD. We show that UBOOD produces reliable classification results when combined with ensemble-based estimators.
  arXiv  Detail & Related papers  (2019-12-31T09:52:49Z)

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.