Uncertainty Sampling

Follow this topic Ask about this topic

Uncertainty sampling studies how to choose the next examples or computations by estimating where a model is unsure, often to reduce labeling or simulation costs. Common approaches rank items by predictive entropy, least confidence, or margin, and use Bayesian variance or ensembles to distinguish uncertainty from data noise; many combine these scores with diversity or coverage. The methods are used in active learning for image, video, and object detection, domain adaptation on retrieval benchmarks such as BEIR, scientific simulation, and efficient model evaluation. A central challenge is that uncertain examples can be redundant, noisy, or poorly matched to the task, so the best strategy depends on the data, budget, and evaluation goal.

Latest papers

23 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coverage
Oct 14, 2026My Tra Nguyen Huynh, Viet Cuong TaDomain Adaptation Active Learning
VNU University of Engineering and Technology, Hanoi, 100000, Vietnam.
Understanding Hidden Spatial Preferences in Bayesian Optimization
Oct 10, 2026Maria Bånkestad, Jens SjölundBayesian Optimization Uncertainty-Aware Exploration
Benchmarking Active Spot Selection for Cost-Efficient Spatial Transcriptomics
Sep 23, 2026Zheyu Zhu, Junchao Zhu, Fengbei Liu +7Spatial Transcriptomics Active Learning
University of Pennsylvania, Philadelphia, PA 19104, USA · Vanderbilt University, Nashville, TN, USA · Cornell Tech, New York, NY 10044, USA +4
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers
Sep 1, 2026Giovanni Bonetta, Matteo Merler, Davide Zago +2Uncertainty Sampling Visual RL
Department of Computer Science, University of Torino, Torino, Italy · Natural Language Processing Unit, Fondazione Bruno Kessler, Trento, Italy
Spending Scarce Confirmatory PET Measurements: Target-Aligned Validation in A4/LEARN
Aug 23, 2026Eliuvish Han Cui, Qiang Yang, Meredith Mengmeng ZhangAdaptive Sampling Uncertainty Sampling
Clinical Functional Service Provider (cFSP) Department, Kuntuo, an IQVIA company · Department of Biostatistics, University of California, Los Angeles · Department of Biometrics, Hengrui Pharmaceuticals
Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction
Jul 30, 2026Gousia Habib, Laura Ruotsalainen3D Reconstruction Neural Rendering
Department of Computer Science, University of Helsinki, Finland
One-step lowest-variance selection in a Gaussian random-field model motivated by masked diffusion: Total correlation and a square root collision threshold
Jul 20, 2026Linjun LiMasked Diffusion Models Parallel Decoding
Department of Mathematics, University of Pennsylvania, Philadelphia, PA.
Adaptive Diversity-Uncertainty Active Learning with Redundancy Control for Bioacoustic Event Classification
Jul 6, 2026Gabriel Dubus, Hugo Magaldi, Anatole Gros-MartialMulti-Label Classification Active Learning
Eco-Anthropologie, Mus´eum National d’Histoire Naturelle, UMR7206, CNRS, Paris, France · Centre d’Etudes Biologiques de Chiz´e, UMR 7372, CNRS, La Rochelle Universit´e, France
Active Learning for Cascaded Object Detection: Balancing Coverage and Uncertainty in Table Extraction Pipelines
Jul 1, 2026Eliott Thomas, Mickael Coustaty, Aurelie Joseph +3Table Structure Recognition Document Information Extraction
L3i, La Rochelle Université, La Rochelle, France · Yooz, Aimargues, France
CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes
Jun 18, 2026Zhijian Zhou, Zesheng Ye, Zhaorun Chen +2LLM Evaluation Anytime-Valid Inference
The University of Melbourne · Department of Computer Science, University of Chicago · Department of Computer Science, University of Illinois Urbana-Champaign
Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning
May 26, 2026Manh Nguyen, Sunil Gupta, Hung LeEfficient Language Model Reasoning Adaptive Sampling
Applied Artificial Intelligence Initiative Deakin University, Australia
OnceSelect: Reusable Data Selection for Efficient Multimodal Instruction Tuning
May 26, 2026Mingkang Dong, Muxin Pu, Hongyi Cai +5Instruction-Tuning Data Selection Multimodal Large Language Models
Faculty of Computer Science Universiti Malaya Kuala Lumpur, Malaysia · School of Information Technology Monash University Malaysia Subang Jaya, Selangor, Malaysia · Faculty of Computer Science University of Science and Technology Beijing Beijing, China
Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning
May 21, 2026Vipul Arya, S. H. Shabbeer Basha, Srikrishna U N +2Active Learning Uncertainty Sampling
School of Computer Science and Engineering, RV University, Bengaluru, Karnataka-560059, India · School of Engineering & Technology, Vidyashilp University, Bangalore, India · Shiv Nadar Institution of Eminence, Delhi NCR
LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields
May 15, 2026Dongjae Lee, Wooseong Yang, Yifu Tao +2Simultaneous Localization and Mapping Replay-Based Continual Learning
Department of Mechanical Engineering, Seoul National University, S. Korea · Oxford Robotics Institute at the University of Oxford, UK
Portable Active Learning for Object Detection
May 11, 2026Rashi Sharma, Justin Timothy C. Bersamin, Karthikk SubramanianActive Learning Uncertainty Sampling
Panasonic R&D Center Singapore · Nanyang Technological University
Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object Tracking
May 11, 2026Riku Inoue, Shogo Sato, Kazuhiko Murasaki +3Active Learning Uncertainty Sampling
NTT, Inc., Kanagawa, Japan
UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval
Apr 28, 2026Jongyoon Kim, Minseong Hwang, Seung-won HwangUnsupervised Domain Adaptation Domain Adaptation
Interdisciplinary Program in Artificial Intelligence, Seoul National University
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
Mar 26, 2026Jiahao Wu, Ning Lu, Shengcai Liu +6Prompt Selection for RL RL for Language Models
Southern University of Science and Technology · The Hong Kong Polytechnic University · The Hong Kong University of Science and Technology +3
Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
Mar 11, 2026Chen-Chen Zong, Sheng-Jun HuangActive Learning Federated Learning
Nanjing University of Aeronautics and Astronautics, China
ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning
Mar 10, 2026Davit Melikidze, Marian Schneider, Jessica Lam +4Data Selection Active Learning
ETH Zurich · Institute of Neuroinformatics, University of Zurich and ETH Zurich · ETH AI Center
Active Learning for Planet Habitability Classification under Extreme Class Imbalance
Feb 27, 2026R. I. El-Kholy, Z. M. HaymanActive Learning Class-Imbalanced Learning
Department of Astronomy, Space Science, and Meteorology Faculty of Science, Cairo University 1 Gamaa Street, Giza 12613, Egypt
Generative Active Testing: Efficient LLM Evaluation via Proxy Task Adaptation
Feb 26, 2026Aashish Anantha Ramakrishnan, Ardavan Saeedi, Hamid Reza Hassanzadeh +2LLM Evaluation Uncertainty Sampling
The Pennsylvania State University · Optum AI
Adaptive Uncertainty-Guided Surrogates for Efficient phase field Modeling of Dendritic Solidification
Feb 17, 2026Eider Garate-Perez, Kerman López de Calle-Etxabe, Oihana Garcia +3Surrogate Modeling Computational Materials Science
Intelligent Information Systems, Tekniker, Iñaki Goenaga 5, Eibar (20600) Spain · Faculty of Informatics UPV-EHU, Paseo Manuel de Lardizabal 1, Donostia (20700) Spain · Department of Computer Sciences and Artificial Intelligence, UPV-EHU, Donostia (20700) Spain +1

Oct 14, 2026J/K move · Enter open · S save

Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coverage

My Tra Nguyen Huynh, Viet Cuong Ta

VNU University of Engineering and Technology, Hanoi, 100000, Vietnam.

Domain Adaptation Active Learning Uncertainty Sampling

Open paper AskPDF arXiv

Active domain adaptation researches focus on alleviating the annotation cost, which comprises source data and target data labelling, as well as enhancing the performance of unsupervised domain adaptation. However, optimizing the adaptation model based on the average accuracy can lead to the drop in performance of some difficult categories. To overcome this issue, a point-wise selection strategy built upon the influence function can be used to improve domain adaptation performance. In our work, we first address the sensitive and redundant aspects of point-wise selection, which can lead to overfitting of the acquisition function. We thus introduce a region-based approach that ensures the improvement of the adaptation model by maximizing a positive manifold coverage. An uncertainty score is further introduced to the selection mechanism to learn a better decision boundary for the target domain. In comprehensive experiments, our proposed method surpasses the first category-aware active domain adaptation baseline as well as existing active domain adaptation methods across multiple domain adaptation benchmarks. Our implementation is available at: https://github.com/nhtm2702/WHO IS NEXT.