Evidence-Guided Unknown Rejection for High-Confidence Near-Known Unknowns

• URL: http://arxiv.org/abs/2605.17818v1
• Date: Mon, 18 May 2026 03:46:55 GMT
• Title: Evidence-Guided Unknown Rejection for High-Confidence Near-Known Unknowns
• Abstract summary: We show that open-set recognition systems face a neglected failure mode: high-confidence near-known unknowns.<n>We propose EGUR-A, which changes the decision from is this sample's score high enough?'' to does this predicted known class have sufficient evidence to accept this sample?''
• Score: 4.320698236637654
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-set recognition systems face a neglected failure mode: high-confidence near-known unknowns, which lie outside the known label set but are close enough to known classes that a closed-set classifier accepts them with high confidence. We show that this failure is widespread across scalar-threshold methods, including recent post-hoc detectors, and that stronger encoders can amplify rather than remove the risk. We propose EGUR-A, which changes the decision from ``is this sample's score high enough?'' to ``does this predicted known class have sufficient evidence to accept this sample?'' EGUR-A combines class-conditional local acceptance evidence with global residual evidence, and selects their relative weight from known-sample statistics without unknown validation data. Across CUB, FGVC-Aircraft, and ImageNet-hard, EGUR-A substantially reduces high-confidence false known acceptance at matched known-rejection operating points. The result is not a stronger threshold; it is a different question: whether a known class is entitled to accept a sample.

Related papers

• Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning [78.92934995292113]
  We propose a Confidence-Aware Asymmetric Learning (CAL) framework, which balances confidence across known and novel forgery types.<n>CAL consistently outperforms previous methods, achieving new state-of-the-art performance on both known and novel forgery attribution.
  arXiv  Detail & Related papers  (2025-12-14T12:31:28Z)
• Known Meets Unknown: Mitigating Overconfidence in Open Set Recognition [4.377912830814393]
  Open Set Recognition (OSR) requires models to accurately classify known classes and to effectively reject unknown samples.<n>When unknown samples are semantically similar to known classes, inter-class overlap in the feature space often causes models to assign unjustifiably high confidence to them.<n>We propose a framework that explicitly mitigates overconfidence caused by inter-class overlap.
  arXiv  Detail & Related papers  (2025-11-15T09:56:44Z)
• Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation [108.13261761812517]
  We introduce FRANQ (Faithfulness-based Retrieval Augmented UNcertainty Quantification), a novel method for hallucination detection in RAG outputs.<n>We present a new long-form Question Answering (QA) dataset annotated for both factuality and faithfulness.
  arXiv  Detail & Related papers  (2025-05-27T11:56:59Z)
• Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundary [10.054397736100245]
  Few-shot Open-set Object Detection (FOOD) poses a challenge in many open-world scenarios.<n>It aims to train an open-set detector to detect known objects while rejecting unknowns with scarce training samples.<n>Our method achieves superior performance over previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-06-26T15:48:24Z)
• Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
  We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors. We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
  arXiv  Detail & Related papers  (2024-03-05T11:44:14Z)
• Taking Class Imbalance Into Account in Open Set Recognition Evaluation [0.3626013617212667]
  This work looks at the evaluation of methods for Open Set Recognition. As an outcome of problem analysis, we present a set of guidelines for evaluation of methods in this field.
  arXiv  Detail & Related papers  (2024-02-09T11:15:49Z)
• Binary Classification with Confidence Difference [100.08818204756093]
  This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
  arXiv  Detail & Related papers  (2023-10-09T11:44:50Z)
• OpenMix: Exploring Outlier Samples for Misclassification Detection [37.43981354073841]
  We exploit the easily available outlier samples, i.e., unlabeled samples coming from non-target classes, for helping detect misclassification errors. We propose a novel method called OpenMix, which incorporates open-world knowledge by learning to reject uncertain pseudo-samples generated via outlier transformation.
  arXiv  Detail & Related papers  (2023-03-30T01:47:23Z)
• What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization [68.15353480798244]
  Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models. Recent years have seen a steep rise in UQ methods that can flag suspicious examples. We propose a framework for categorizing uncertain examples flagged by UQ methods in classification tasks.
  arXiv  Detail & Related papers  (2022-07-11T19:47:00Z)
• Open Set Recognition with Conditional Probabilistic Generative Models [51.40872765917125]
  We propose Conditional Probabilistic Generative Models (CPGM) for open set recognition. CPGM can detect unknown samples but also classify known classes by forcing different latent features to approximate conditional Gaussian distributions. Experiment results on multiple benchmark datasets reveal that the proposed method significantly outperforms the baselines.
  arXiv  Detail & Related papers  (2020-08-12T06:23:49Z)
• Conditional Gaussian Distribution Learning for Open Set Recognition [10.90687687505665]
  We propose Conditional Gaussian Distribution Learning (CGDL) for open set recognition. In addition to detecting unknown samples, this method can also classify known samples by forcing different latent features to approximate different Gaussian models. Experiments on several standard image reveal that the proposed method significantly outperforms the baseline method and achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2020-03-19T14:32:08Z)

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.