Weakly Supervised Learning

Overview

Weakly supervised learning studies how to train useful models when labels are missing, noisy, ambiguous, or available only for groups of examples rather than individual instances. Common approaches include multiple-instance learning, positive-unlabeled and partial-label learning, learning from label proportions, and pseudo-labeling or combining heuristic labeling functions. These methods support tasks such as finding objects in images with only image-level labels, locating events in videos with sparse timestamps, and classifying medical scans from patient-level diagnoses. A central challenge is that weak labels can encode bias or shift across settings, so reliable evaluation and deciding when a label or localized prediction can be trusted remain open concerns.

Latest papers

CardsList

163 papers9 papers in the last four weeks, down 53% on the four weeks before. 0.1% of all new papers.

  1. Arbor: When Labels Are Not Coarsened at Random

    Nov 11, 2026Faisal Mohammad, Mohamed YounisFine-Grained Image ClassificationHierarchical Classification

  2. Towards Label-Efficient Geospatial Foundation Model Adaptation via Positive-Unlabeled Learning for Building Damage Mapping

    Nov 5, 2026Hengwei Zhao, Qirui Wang, Zhuo Zheng +3Geospatial Foundation ModelsBuilding Damage Assessment

  3. Constructing a Regional Slang Lexicon for Electricity Demands via Soft-Label Bidirectional Anchoring and Active Learning

    Nov 3, 2026Rong Chang, Lijing Shi, Zhaoxiang ZangWeakly Supervised LearningLow-Resource Language Processing

  4. Robust EEG-based Emotion Recognition from Coarse Trial-level Labels under Intra-trial Affective Variability

    Nov 1, 2026Xiaocong Zeng, Buxuan Wang, Xin Yang +2EEG Emotion RecognitionAffective Computing

  5. Sounding Surgical Instrument Localisation through Audio-Visual Correspondence

    Oct 23, 2026Dominic Behling, Jonas Hein, Matthias SeiboldSurgical Instrument TrackingAudio-Visual Understanding

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

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

  7. Soft Ontology Priors over Latent Concept Posteriors for Weakly Supervised Neuro-Symbolic Learning

    Oct 21, 2026Tengwei Song, Robert HoehndorfNeurosymbolic LearningWeakly Supervised Learning

  8. IECG: Weakly-Supervised Interpretability-Enhancing Foundation Model for Electrocardiogram

    Oct 20, 2026Huynh Dang Nguyen, Trong-Thang Pham, Anh-Thuan Do +4Electrocardiogram Foundation ModelsElectrocardiogram Interpretation

  9. Beyond the Dominant Label: Recovering Coexisting Lesion Evidence with Multiple Instance Learning

    Oct 15, 2026Lubin Gan, Jing Zhang, Xinming Zhang +3Multiple Instance LearningWhole-Slide Image Analysis

  10. Rethinking Learning from Label Proportions via Moment Matching

    Oct 15, 2026Tianhao Ma, Wei Wang, Yivan Zhang +4Moment MatchingWeakly Supervised Learning

  11. LLM-Based Weak Annotation for Cybersecurity Tweet Classification: A Teacher-Student Framework

    Oct 15, 2026Ferry Afit Kurniawan, Kazushi Okamoto, Koki Karube +2LLM-Assisted AnnotationText Classification

  12. RespFocus: Learning Temporal Evidence for Weakly Supervised Respiratory Sound Classification

    Oct 11, 2026Yi Tian, Xiaohuan Chen, Yufei tang +5Respiratory Sound ClassificationWeakly Supervised Learning

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

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

  14. Model-agnostic Knowledge Augmented Machine Learning for Weakly Annotated Bioimaging Data

    Oct 9, 2026Jayanie Bogahawatte, Sachith Seneviratne, Simon Maksour +6Weakly Supervised Learning

  15. A Proof-of-Concept Study of Weakly Supervised Labeling of Fine-Grained EEG Components for Artifact Attenuation

    Oct 7, 2026Lu Wang-Nöth, Hai Huang, Philipp Heiler +3EEG Artifact RemovalElectroencephalography

  16. STORK: Spatio-Temporal Observation of uterine contRactions via neural networKs

    Oct 7, 2026Melissa Schween, Tristan Gottwald, Jordina Aviles Verdera +3Fetal MRIMagnetic Resonance Imaging

  17. WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification

    Oct 5, 2026Turhan Can Kargin, Piotr Kubaty, Ekaterina Rostovskaya +3Animal Re-IdentificationImage Matching

  18. Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning

    Oct 5, 2026Lingyu Shen, Wei Tang, Fakhri Karray +1Weakly Supervised LearningMultiple Instance Learning

  19. Calibrated Weak Supervision for Post-Harvest Burned-Cropland Mapping Under Label Scarcity

    Oct 4, 2026Raunak Bhagate, Maitri Polisetty, R I MinuPost-Hoc CalibrationAgricultural Remote Sensing

  20. From Change Captions to Change Detection: Semantic-Appearance Agreement Framework for Remote Sensing Change Detection

    Sep 23, 2026Yuan Qian, Jie MaRemote Sensing Change DetectionRemote Sensing

  21. Weakly Supervised Quantum Error Mitigation

    Sep 22, 2026Seyed Mohamad Ali Tousi, G. N. DeSouzaWeakly Supervised LearningQuantum Error Mitigation

  22. SomaNet: Weakly Supervised Learning for Instance Soma Segmentation in 3D Electron Microscopy with Partial Annotations

    Sep 19, 2026Mohammad Khateri, Morteza Ghahremani, Jussi Tohka +1Electron MicroscopyInstance Segmentation

  23. Building Trustworthy Mental Health Benchmarks on Bluesky: A Validation-Aware Weak-Supervision Framework

    Sep 19, 2026Gaurab Chhetri, Anandi Dutta, Subasish DasMental HealthSocial Media Analysis