Pseudo-Labeling

Ask about this topic

Overview

Pseudo-labeling studies how to use model-generated labels to learn from unlabeled examples, making it useful when human annotation is scarce or expensive. Common approaches include teacher–student self-training, confidence thresholding, consistency training, and iterative refinement, with applications spanning image segmentation, speech recognition, domain adaptation, and graph learning. Recent methods add calibration, uncertainty estimates, foundation-model cues, or temporal and multimodal agreement to decide which predictions to trust. The central tension is that more pseudo-labels increase coverage but can also amplify errors and confirmation bias, so gains depend on label quality, distribution shift, and the task.

Latest papers

CardsList

159 papers16 papers in the last four weeks, down 36% on the four weeks before. 0.1% of all new papers.

  1. Quantum-Inspired Convolutional Networks for High-Resolution Pseudo-Label Generation from Multimodal Earth Observation Data

    Oct 29, 2026Abhishek Singh, Giovanni Cuozzo, Alexander Jacob +1Pseudo-LabelingWeakly Supervised Semantic Segmentation

    Institute for Earth Observation, Eurac Research, Bolzano, Italy

  2. Self-Labeled Preference Transfer for Steerable Robot Manipulation

    Oct 27, 2026Kaiwen Hong, Shaoting Peng, Xiangyu Zeng +6VLA Model AdaptationRobotic Manipulation

    University of Illinois Urbana-Champaign · University of California, Berkeley · Harvard University +2

  3. HDVS: semi-supervised semantic segmentation via heterogeneous dual-branch voting supervision

    Oct 27, 2026Yongqi Shan, Yunzhi Zhuge, Huchuan LuSemantic SegmentationPseudo-Labeling

    School of Computer Science and Technology, Dalian University of Technology, Dalian 116081, China. · School of Information and Communication Engineering, Dalian University of Technology, Dalian 116081, China.

  4. Learning High-Quality Pseudo-Labels for Point-Supervised Temporal Action Localization

    Oct 26, 2026Zhenying FangTemporal Action LocalizationTemporal Video Understanding

    Independent Researcher

  5. Should Pseudo-Labels Share Mini-Batches with Labeled Examples? Semi-Supervised Continual Active Learning with Limited Training Cost

    Oct 26, 2026Shiqi Zhang, Tuomas VirtanenActive LearningPseudo-Labeling

    Faculty of Information Technology and Communication Sciences Tampere University, Tampere, Finland

  6. P2P-Former: Bridging the Supervision Gap Between Point and Proposal in Temporal Action Localization

    Oct 25, 2026Yunchuan Ma, Laiyun Qing, Sai Xu +2Temporal Action LocalizationTemporal Video Understanding

    University of Chinese Academy of Sciences, Beijing,100190, China

  7. RoleHear: Pseudo-Labeling for Semi-Supervised Role-Attributed Streaming Speech Recognition

    Oct 24, 2026Zefang Liu, Chenyang Zhu, Sangwoo Cho +4Speaker-Attributed ASRAutomatic Speech Recognition

    Capital One, USA

  8. STEP: Surgical Point Tracking from Sparse Endpoints and Pseudo-trajectories

    Oct 22, 2026Bing Fan, Anwesa Choudhuri, Zhongpai Gao +5Point TrackingWeakly Supervised Learning

    United Imaging Intelligence, Boston, MA, USA · University of North Texas, Denton, TX, USA

  9. Open-Vocabulary Models and Label Propagation for Uncertainty-aware Pseudo-Labeling of Object Detection Datasets

    Oct 21, 2026Jonathan Klees, Timo Heller, Matthias RottmannPseudo-LabelingObject Detection

    Institute of Computer Science, Osnabrück University · Department of Mathematics, University of Wuppertal

  10. TEMPL: A Resource-Efficient and Transparent Model-Free Framework for Pseudo-Label Generation in Material CT Scans

    Oct 20, 2026Ashiqur Rahman, Venkata Devesh Reddy Seethi, Austin Yunker +2Image SegmentationPseudo-Labeling

    Department of Computer Science, Northern Illinois University, DeKalb, IL, USA · Argonne National Laboratory, Lemont, IL, USA

  11. Progressive Subset Selection and Cascaded Consistency for Unsupervised Vision-Language Model Adaptation

    Oct 20, 2026Hao Yan, Guanghui WangVLM AdaptationUnsupervised Domain Adaptation

    Department of Computer Science, Toronto Metropolitan University, Toronto, ON, Canada

  12. Confidence-Guided Pseudo-Label Refinement for Unsupervised Cross-Domain Person Re-Identification

    Oct 19, 2026Sundas Iqbal, Danish Ali, Qing Tian +3Person Re-IdentificationUnsupervised Domain Adaptation

    School of Software, Nanjing University of Information Science and Technology, Nanjing 210044, China · School of Computer Science, Wuhan University, Wuhan 430072, China · School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China +5

  13. Cross-polarization pairing for label-free few-shot thin-section classification

    Oct 17, 2026Bingchen YanFew-Shot Image ClassificationMicroscopy Image Analysis

    School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, 541004, China

  14. Hybrid supervised instance segmentation by learning label noise suppression

    Oct 14, 2026Linwei Chen, Ying Fu, Shaodi You +1Instance SegmentationPseudo-Labeling

    School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China · Computer Vision Research Group, Insititute of Informatics, University of Amsterdam, Amsterdam 1098 XH, Netherlands · Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing 100101, China

  15. Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via Movement

    Oct 11, 2026Yanan Ma, Yihang Tao, Zhengru Fang +3Test-Time AdaptationUnsupervised Domain Adaptation

    Department of Computer Science, City University of Hong Kong · Department of Electrical and Computer Engineering, The University of Hong Kong

  16. ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology

    Oct 11, 2026Chen Shu, Chengyang Zhang, Boyu Fu +5Weakly Supervised LearningComputational Pathology

    College of Computer Science, Sichuan University, Chengdu, China · Institute of Clinical Pathology, West China Hospital, Sichuan University, Chengdu, China · Pittsburgh Institute, Sichuan University, Chengdu, China +1

  17. Constructing Structured Decision Sources for Consensus-Based Pseudo-Label Learning

    Oct 8, 2026Long WangPseudo-LabelingEnsemble Diversity

  18. Unsupervised Long-Tailed Adaptation of Vision-Language Models

    Oct 6, 2026Keliang Chen, Yaxin Hou, Hui Liu +1Long-Tail LearningVLM Adaptation

    School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · School of Computing and Information Sciences, Saint Francis University, Hong Kong, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China

  19. Candidate Retention for Abductive Learning

    Sep 30, 2026Hao-Yuan He, Yu Liu, Ming LiAbductive ReasoningPseudo-Labeling

    School of Artificial Intelligence, Nanjing University · National Key Laboratory for Novel Software Technology, Nanjing University

  20. ProGuT: Label-Efficient Panoptic Segmentation for Forest Scenes

    Sep 29, 2026Pankaj Deoli, Karsten BernsImage SegmentationPanoptic Segmentation

    Robotics Research Lab, RPTU Kaiserslautern-Landau Gottlieb-Daimler-Str. 48, 67663 Kaiserslautern, Germany

  21. OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute

    Sep 28, 2026Brandon Leblanc, Charalambos PoullisMulti-View 3D ReconstructionPseudo-Labeling

    Immersive and Creative Technologies Lab, Concordia University, Montreal, Canada

  22. Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges

    Sep 27, 2026Donghao Huang, Jinling Pei, Zhaoxia WangLLM-as-a-JudgeSelective Prediction

    Research and Development, Mastercard, Arlington, VA, USA · School of Computing and Information Systems, Singapore Management University, Singapore

  23. An Active-Bottleneck Mechanism for Weak-to-Strong Generalization

    Sep 27, 2026Mohammad Zeinalpour, Amir NajafiWeak-to-Strong GeneralizationRandom Feature Methods

    Department of Computer Engineering, Sharif University of Technology

  24. When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling

    Sep 27, 2026Ping Guo, Zhiqi Huang, Xinran LiImage SegmentationLong-Tail Learning

    Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan · School of Software, Dalian University of Technology, Dalian, China · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China

  25. Pretrained ASR Pseudo-labeling for Noisy Police Audio

    Sep 24, 2026Kaavya Chaparala, Su Huang, Stephen L. Morgan +2Domain Adaptation for ASRAutomatic Speech Recognition

    Johns Hopkins University, Baltimore, USA · Providence College, Providence, USA

  26. Can Frozen Hyperspherical Features Guide the Selection of Pseudo Masks?

    Sep 24, 2026Xinge Guo, Fengyang Xiao, Dingming Zhang +6Promptable Image SegmentationPseudo-Labeling

    Duke University · Carnegie Mellon University · University of Alabama at Birmingham

  27. SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting

    Sep 24, 2026Nitya Nanvani, Andras Palffy, Holger Caesar3D Gaussian Splatting3D Semantic Segmentation

    Perciv AI, The Netherlands · Delft University of Technology, The Netherlands

  28. Label-Efficient Learning for Ground-Based Sky-Image Classification: A Benchmark of Transfer Learning, Active Learning, and Pseudo-Labeling on GCD

    Sep 22, 2026Esther Bou Dagher, Viktoriya Bu-Dager, Boguslaw ZegarlinskiActive LearningTransfer Learning

    CEREMADE, Universit´e Paris Dauphine-PSL, Paris, France. · School of Computing and Information Science, Anglia Ruskin University, Cambridge, United Kingdom. · Institute of Mathematics, Polish Academy of Sciences, Warsaw, Poland.

  29. From Reliable Text to Real Voices: Trust-Aware Progressive Adaptation for Low-Resource TTS

    Sep 22, 2026Jiayi Lu, Yizhong Geng, Jinghan Yang +4Synthetic-to-Real Domain AdaptationLow-Resource TTS Synthesis

    Beijing Logic Intelligence Technology · University of Washington · Beijing University of Posts and Telecommunications +2

  30. Real-World Perception for Autonomous Driving in Adverse Weather: Enhancing Standard Detectors via Foundation-Guided Auto-Annotation

    Sep 22, 2026Sepideh Gohari, Goodarz Mehr, Azim EskandarianAutonomous Driving PerceptionObject Detection

    Autonomous Robots and Vehicles Laboratory (ARVL), College of Engineering, Virginia Commonwealth University (VCU), Richmond, Virginia, United States