Cross-Dataset Generalization

Ask about this topic

Overview

Cross-dataset generalization studies whether a model trained on one dataset can work on data from different hospitals, populations, devices, languages, or environments. Researchers test this with external validation and leave-one-dataset-out benchmarks, and try to improve transfer through diverse multi-source training, domain adaptation, robust representations, data augmentation, and limited target-domain fine-tuning. Results often show a gap between strong in-dataset scores and performance on new sources, so evaluation increasingly considers calibration, class-specific errors, and decision thresholds as well as accuracy. A central tension is that methods that remove source-specific signals may also discard useful information, while differences in measurement, labels, and data quality can make apparent model failures—or gains—hard to interpret.

Latest papers

CardsList

142 papers19 papers in the last four weeks, up 27% on the four weeks before. 0.1% of all new papers.

  1. Feature-level Site Leakage Reduction for Cross-Hospital Chest X-ray Transfer via Self-Supervised Learning

    Mar 31, 2026Ayoub Louaye Bouaziz, Lokmane CheboubaCross-Domain Transfer LearningCross-Dataset Generalization

    University of Mentouri Brothers Constantine 1, Constantine, Algeria · University of Paris-VIII-Vincennes-Saint-Denis, France · LRIA Laboratory, University of Science and Technology Houari Boumediene (USTHB), Bab-Ezzouar, Algeria +1

  2. A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators

    Mar 29, 2026Lam Pham, Khoi Vu, Dat Tran +4Audio Deepfake DetectionTraining Data Curation

    Austrian Institute of Technology, Austria. · FPT University, Vietnam. · Singapore Institute of Technology, Singapore.

  3. SteelDefectX: A Multi-Form Vision-Language Dataset and Benchmark for Steel Surface Defect Analysis

    Mar 23, 2026Shuxian Zhao, Jie Gui, Baosheng Yu +1VLM EvaluationVision-Language Grounding

    Southeast University · Purple Mountain Laboratories · Nanyang Technological University

  4. Evaluating Test-Time Adaptation For Facial Expression Recognition Under Natural Cross-Dataset Distribution Shifts

    Mar 20, 2026John Turnbull, Shivam Grover, Amin Jalali +1Test-Time AdaptationDistribution Shift Robustness

    Department of Electrical and Computer Engineering, Queen’s University, Kingston, Canada

  5. Prompt-Free Lightweight SAM Adaptation for Histopathology Nuclei Segmentation with Strong Cross-Dataset Generalization

    Mar 20, 2026Muhammad Hassan Maqsood, Yanming Zhu, Alfred Lam +3Histopathology Image SegmentationVision Foundation Model Adaptation

    School of Information and Communication Technology, Griffith University, QLD, Australia · School of MDP – Clinical Medicine, Griffith University, QLD, Australia

  6. Towards One-for-All Anomaly Detection for Tabular Data

    Mar 15, 2026Shiyuan Li, Yixin Liu, Yu Zheng +3Tabular Anomaly DetectionAnomaly Detection

    Griffith University, Gold Coast, Australia · Tongji University, Shanghai, China

  7. TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detection

    Mar 10, 2026Xiong Zhang, Hong Peng, Changlong Fu +3Anomaly DetectionCross-Dataset Generalization

    School of Software and AI, Yunnan University, Kunming, China

  8. Adversarial Domain Adaptation Enables Knowledge Transfer Across Heterogeneous RNA-Seq Datasets

    Mar 9, 2026Kevin Dradjat, Massinissa Hamidi, Blaise HanczarCancer Subtype ClassificationDomain Adaptation

    IBISC Laboratory, University Paris-Saclay (Univ. Evry), France · ADLIN, Paris, France

  9. AgrI Challenge: A Data-Centric AI Competition for Cross-Team Validation in Agricultural Vision

    Mar 7, 2026Mohammed Brahimi, Karim Laabassi, Mohamed Seghir Hadj Ameur +7Cross-Dataset GeneralizationDomain Generalization

    The National School of Artificial Intelligence (ENSIA), Algiers, 16046, Algeria · National Higher School of Agronomy (ENSA), Algiers, 16051, Algeria · National Higher School of Computer Science (ESI), Algiers, 16000, Algeria +1

  10. LF2L: Loss Fusion Horizontal Federated Learning Across Heterogeneous Feature Spaces Using External Datasets Effectively: A Case Study in Second Primary Cancer Prediction

    Mar 7, 2026Chia-Fu Lin, Yi-Ju TsengFederated LearningHeterogeneous Federated Learning

    Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan

  11. AdaBox: Adaptive Density-Based Box Clustering with Parameter Generalization

    Mar 6, 2026Ahmed ElmahdiDensity-Based ClusteringClustering

    Independent Researcher

  12. Task Expansion and Cross Refinement for Open-World Conditional Modeling

    Mar 3, 2026Shreyas Bhat Brahmavar, Qiyang Liu, Yang Li +1Cross-Dataset GeneralizationSemi-Supervised Learning

    Department of Computer Science, University of North Carolina at Chapel Hill · Independent Researcher

  13. Piecing Together Cross-Document Coreference Resolution Datasets: Systematic Dataset Analysis and Unification

    Feb 28, 2026Anastasia Zhukova, Terry Ruas, Jan Philip Wahle +1Coreference ResolutionCross-Dataset Generalization

    University of Göttingen Göttingen, Germany

  14. Exploring Robust Intrusion Detection: A Benchmark Study of Feature Transferability in IoT Botnet Attack Detection

    Feb 27, 2026Alejandro Guerra-Manzanares, Jialin HuangIoT Intrusion DetectionCross-Domain Generalization

    School of Computer Science, University of Nottingham, Ningbo, China · School of Computer Science, University of Nottingham, Nottingham, United Kingdom

  15. Effects of Training Data Quality on Classifier Performance

    Feb 25, 2026Alan F. Karr, Regina RuaneTraining Data CurationCross-Dataset Generalization

    Fraunhofer USA Center Mid-Atlantic, Riverdale MD 20737 · Computational Social Science Laboratory, University of Pennsylvania, Philadelphia, PA 19104

  16. CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG

    Feb 22, 2026Xiaobin Wong, Zhonghua Zhao, Haoran Guo +5Cross-Dataset GeneralizationCross-Domain Generalization

    Tsinghua Laboratory of Brain and Intelligence · Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences +6

  17. Improving Generalizability of Hip Fracture Risk Prediction via Domain Adaptation Across Multiple Cohorts

    Feb 20, 2026Shuo Sun, Meiling Zhou, Chen Zhao +8Cross-Dataset GeneralizationClinical Risk Prediction

    Department of Mathematical Sciences, Michigan Technological University, Houghton, MI, USA · Department of Statistics, Grand Valley State University, Allendale, MI, USA · Department of Computer Science, Kennesaw State University, Marietta, GA, USA +6

  18. Generalization from Low- to Moderate-Resolution Spectra with Neural Networks for Stellar Parameter Estimation: A Case Study with DESI

    Feb 16, 2026Xiaosheng Zhao, Yuan-Sen Ting, Rosemary F. G. Wyse +5Cross-Dataset GeneralizationTransfer Learning

    Department of Physics & Astronomy, The Johns Hopkins University, Baltimore, MD 21218, USA · Department of Astronomy, The Ohio State University, 140 West 18th Avenue, Columbus, OH 43210, USA · Center for Cosmology and AstroParticle Physics (CCAPP), The Ohio State University, Columbus, OH 43210, USA +6

  19. Federated Learning for Surgical Vision in Appendicitis Classification: Results of the FedSurg EndoVis 2024 Challenge

    Oct 6, 2025Max Kirchner, Hanna Hoffmann, Alexander C. Jenke +16Surgical Video UnderstandingCross-Dataset Generalization

  20. Glucose-ML: A collection of longitudinal diabetes datasets for development of robust AI solutions

    Jul 18, 2025Temiloluwa Prioleau, Baiying Lu, Yanjun CuiForecasting BenchmarksBlood Glucose Forecasting

    Department of Computer Science Emory University Atlanta, GA 30322 · Department of Computer Science Dartmouth College Hanover, NH 03755

  21. Label Unification for Cross-Dataset Generalization in Cybersecurity NER

    Jul 18, 2025Maciej Jalocha, Johan Hausted Schmidt, William MichelsenCross-Dataset GeneralizationNamed Entity Recognition

  22. Can Argus Judge Them All? Comparing VLMs Across Domains

    Jun 23, 2025Harsh Joshi, Gautam Siddharth Kashyap, Rafiq Ali +5VLM EvaluationVLM Robustness

    Bharati Vidyapeeth, New Delhi, India · Macquarie University, Sydney, Australia · DSEU-Okhla, New Delhi, India +3