Pseudo-Label Quality

Follow this topic Ask about this topic

Momentum

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

Jul 6Week of Sep 21

Latest papers 21

All topics

Pseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series Forecasting
Sep 30, 2026Yeryeong Kwak, Yoo-Min Jung, Jonghun ParkRetraining Time Series
Seoul National University Seoul, Republic of Korea
ProGuT: Label-Efficient Panoptic Segmentation for Forest Scenes
Sep 29, 2026Pankaj Deoli, Karsten BernsPanoptic Segmentation Pseudo-Label Quality
Robotics Research Lab, RPTU Kaiserslautern-Landau Gottlieb-Daimler-Str. 48, 67663 Kaiserslautern, Germany
ThreshGuide: Class-Aware Labeled-Guided Thresholding for Semi-Supervised 3D Abdominal Multi-Organ Segmentation
Sep 14, 2026Hongyu Liu, Yinlong Wang, Lusha Li +13D Medical Image Segmentation Semi-Supervised Medical Image Segmentation
School of Intelligent Science and Technology, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China
Beyond Contact Sensors: Deep learning with Pseudo-Labeling for remote Photoplethysmography
Sep 9, 2026Bhargav Acharya, Barbara Hammer, Hanna DrimallaRemote Photoplethysmography Pseudo-Label Quality
Center for Cognitive Interaction Technology (CITEC), Bielefeld University
CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers
Aug 13, 2026Ebenezer TarubingaHigh Confidence Pseudo-Labels Semantic Segmentation
AI Research Department, Ebenworks Systems, Seoul, Korea
PseudoMapLabeler: Confidence-Aware Pseudo-Label Generation for Semi-Supervised Online Mapping
Aug 12, 2026Chikao Tsuchiya, Dhaval Bhanderi, David Ilstrup +2Lane-Level Map Generation High Confidence Pseudo-Labels
Nissan Advanced Technology Center - Silicon Valley, Nissan North America, Santa Clara, CA 95014, USA
Test-Time Curriculum for Open-Set AIGC Detection
Aug 1, 2026Yiqian Zhang, Zheyuan Gu, Xiangzhao Hao +8Ai-Generated Image Detection Ai-Generated Content Detection
Hangzhou Dianzi University · ERNIE Team, Baidu Inc. · Harbin Institute of Technology (Shenzhen)
OFD-Net: Teacher-Free Reliable Semi-supervised Medical Image Segmentation with Orthogonal Feature Disentanglement Net of Foreground-Background
Jul 18, 2026Shao-feng Jiang, Zhe-yang Jing, Qin Lu +4Semi-Supervised Medical Image Segmentation Pseudo-Label Quality
Department of Biomedical Engineering, and the Key Laboratory of Nondestructive Testing, Ministry of Education, Nanchang Hangkong University, Nanchang 330063, China
Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR
Jul 6, 2026Qu Yang, Cakra Wardhana, Tim NgCode-Switching Multilingual Automatic Speech Recognition
Apple, Singapore · National University of Singapore, Singapore
Exploring SAM Supervision for Fine-Grained UAV Target Segmentation under Data Scarcity
Jul 4, 2026Le-Anh TranPseudo-Label Quality Drone Detection
Enhancing BEST-RQ Pseudo-Label Quality through Online Refinement for Automatic Speech Recognition
Jun 24, 2026Jingjing Xu, Zijian Yang, Mohammad Zeineldeen +3Automatic Speech Recognition High Confidence Pseudo-Labels
Machine Learning and Human Language Technology Group, RWTH Aachen University, Germany · Apptek GmbH, Aachen, Germany
Unsupervised Domain Adaptation for Sim-to-Real Object Pose Estimation with Contrastive Alignment and Pseudo-Label Refinement
Jun 19, 2026Nidhal Eddine Chenni, Arunkumar Rathinam, Djamila AouadaCategory-Level Object Pose Estimation Domain Adaptation
SnT, University of Luxembourg
Towards a Pseudo-Labeling Workflow for Celltype-Classification from Explanted Brain Slice Recordings
Jun 15, 2026Cora Jostock, Jonas Ort, Henner Koch +2Neural Recordings Cells
University of Duisburg-Essen, Intelligent Embedded Systems Lab, Duisburg, Germany · RWTH University Hospital, Department of Neurosurgery, Aachen, Germany · RWTH University Hospital, Department of Epileptology, Aachen, Germany
Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification
Jun 2, 2026Jiahui Li, Jianfeng Shan, Wenpei Chen +5Reinforcement Learning With Verifiable Reward LLM Reasoning Strategies
1Sun Yat-Sen University · University of Science and Technology of China · 3National University of Singapore
Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation
May 30, 2026Yingxu Wang, Xinwang Liu, Siyang Gao +1Domain Adaptation High Confidence Pseudo-Labels
Department of Computer Science and Engineering, Chinese University of Hong Kong · College of Computer, National University of Defense Technology, Changsha, 410073, China · Department of Data Science, City University of Hong Kong +1
Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation
May 27, 2026Runlong Cao, Ying Zang, Chuanwei Zhou +4High Confidence Pseudo-Labels Pseudo-Label Quality
School of Computer Science and Engineering, Nanjing University of Science and Technology · School of Information Engineering, Huzhou Normal University · School of Artificial Intelligence, Nanjing University of Posts and Telecommunications +3
STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection
May 20, 2026Yaoteng Zhang, Qing Zhou, Junyu Gao +1Intra-Class Pseudo-Label Quality
School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China · School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, China · Northwestern Polytechnical University, Xi’an 710072, China
COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication
May 11, 2026Ben Rachmut, Luise Ge, William Yeoh +2Federated Learning Personalization
Washington University in St. Louis
EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing
May 9, 2026Huilai Li, Xiaomeng Di, Ying Xing +3Audio-Visual Reasoning Fine-Grained Video Understanding
School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing 100876, China
Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation
Apr 20, 2026Wei Huang, Yuxuan Xiong, Hezhe Qiao +3Graph Anomaly Detection Synthetic Tabular Data
EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection
Mar 12, 2026Shuo Jiang, Gaojia Zhang, Min Tan +2Camouflaged Object Detection Pseudo-Label Quality
Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University · Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University · College of Computer Science and Technology, Zhejiang University

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

Pseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series Forecasting

Yeryeong Kwak, Yoo-Min Jung, Jonghun Park

Seoul National University Seoul, Republic of Korea

Retraining Time Series Non-Stationarity Pseudo-Label Quality

Open paper AskPDF arXiv

Real-world time series forecasting systems operate under non-stationary data streams, where forecasting performance may degrade over time. Although retraining can recover the performance, it incurs non-trivial computational and operational costs. Under limited deployment resources, the key challenge is therefore not only how to retrain but also when to retrain. While existing retraining policies often rely on indirect indicators such as drift alarms or model staleness, we instead use realized forecast errors as direct deployment feedback. In this paper, we propose PILOT (Pseudo-label-Informed Learned Online Trigger), an online retraining framework that learns when to retrain from forecast-error dynamics. Since ground-truth retraining labels are unavailable, PILOT constructs a pseudo-label from future increases in forecast error and trains a lightweight scorer to predict it from observed error states. At deployment, PILOT uses only completed forecast errors and serves as a plug-in module for arbitrary forecasting backbones without architectural modification. We evaluate PILOT under standard multivariate forecasting settings across eight benchmarks with three representative backbones---DLinear, iTransformer, and TimesNet. Across all three backbones, PILOT achieves state-of-the-art average-rank performance among retraining policies while maintaining a favorable performance--efficiency trade-off.

Momentum

Related topics

Latest papers 21