paper-with-me

Papers

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention

2025-05-11 · Alexander Koebler, Thomas Decker, Ingo Thon, Volker Tresp, Florian Buettner

We study the problem of monitoring machine learning models under gradual distribution shifts, where circumstances change slowly over time, often leading to unnoticed yet significant declines in accuracy. To address this, we propose Incremental Uncertainty-aware Performance Monitoring (IUPM), a novel label-free method that estimates performance changes by modeling gradual shifts using optimal transport. In addition, IUPM quantifies the uncertainty in the performance prediction and introduces an active labeling procedure to restore a reliable estimate under a limited labeling budget. Our experiments show that IUPM outperforms existing performance estimation baselines in various gradual shift scenarios and that its uncertainty awareness guides label acquisition more effectively compared to other strategies.

📄 PDF Abstract BibTeX arXiv:2505.07023

Code (1)

alexanderkoebler/IUPM 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Safety-Critical Camera Reliability Monitoring for ADAS via Degradation-Aware Uncertainty Pattern Analysis

2026-05-06 · Shiva Aher arxiv

Reliable camera input is essential for safety-critical ADAS perception, but most monitoring approaches detect sensor failures only after downstream performance has degraded. We propose a proactive camera reliability moni…

Active3D: Active High-Fidelity 3D Reconstruction via Hierarchical Uncertainty Quantification

2025-11-25 · Yan Li, Yingzhao Li, Gim Hee Lee arxiv

In this paper, we present an active exploration framework for high-fidelity 3D reconstruction that incrementally builds a multi-level uncertainty space and selects next-best-views through an uncertainty-driven motion pla…

3D Reconstruction

Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation

2022-08-10 · Findings (NAACL) 2022 7 · Zhijing Wu, Hua Xu, Jingliang Fang, Kai Gao

Continual Machine Reading Comprehension aims to incrementally learn from a continuous data stream across time without access the previous seen data, which is crucial for the development of real-world MRC systems. However…

Domain AdaptationIncremental LearningMachine Reading ComprehensionReading Comprehension

Active Inference for Micro-Gesture Recognition: EFE-Guided Temporal Sampling and Adaptive Learning

2026-03-08 · Weijia Feng, Jingyu Yang, Ruojia Zhang, Fengtao Sun 외 arxiv

Micro-gestures are subtle and transient movements triggered by unconscious neural and emotional activities, holding great potential for human-computer interaction and clinical monitoring. However, their low amplitude, sh…

Micro-gesture Recognition

Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speech

2026-03-20 · Niclas Pokel, Yiming Zhao, Pehuén Moure, Yingqiang Gao 외 arxiv

Personalizing Automatic Speech Recognition (ASR) for non-normative speech remains challenging because data collection is labor-intensive and model training is technically complex. To address these limitations, we propose…

Speech RecognitionActive Learning