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. Normative Deviation Modeling for EEG-based Depression Detection

    Oct 27, 2026Wan Jiang, Jingqi Cheng, Hui Zhang +5Depression DetectionElectroencephalography

    Hefei University of Technology · Anhui University

  2. How Robust Are CNNs and Vision Transformers for Alzheimer's MRI Classification Across Datasets?

    Oct 24, 2026Hafija Aktar, Molly Croes, Frank S. Menniti +1Alzheimer's Disease ClassificationCross-Dataset Generalization

    Department of Computer Science, University of Rhode Island, Kingston, RI 02881, USA · Department of Biomedical and Pharmaceutical Sciences, George & Anne Ryan Institute for Neuroscience, University of Rhode Island, Kingston, RI 02881, USA

  3. ReLEAP: Upcycling Vision Datasets through Cross-Task Unification and Semi-Supervised Annotation

    Oct 23, 2026Julia Simon, Daniel Steininger, Andreas TrondlCross-Dataset GeneralizationSemi-Supervised Learning

    AIT Austrian Institute of Technology, Giefinggasse 4, 1210 Vienna, Austria Center for Vision, Automation & Control

  4. DISC: Domain-Integrated Similarity Cost for Time-Series Dataset

    Oct 22, 2026Yen-Ku Liu, Hongjie Chen, Franck Dernoncourt +1Task Transferability EstimationCross-Dataset Generalization

    National Yang Ming Chiao Tung University · Dolby Laboratories · Adobe Research

  5. Evidence-Guided Selection of Retinal Vessel Segmentation Pipelines: A Cross-Dataset Benchmark of Performance, Structure, Failure Modes, and Reproducibility

    Oct 22, 2026Ruoyu Yan, Yuejia Liu, Shixin Xu +4Retinal Vessel SegmentationOphthalmic Image Analysis

    Duke Kunshan University, Kunshan, China · University of Toronto, Toronto, Canada · Beijing Normal–Hong Kong Baptist University, Zhuhai, China +1

  6. Single-Image Food Mass Estimators Do Not Transfer Their Gram Scale Across Datasets

    Oct 21, 2026Yongsheng LianCross-Dataset GeneralizationVision Foundation Model Adaptation

    University of Louisville, Louisville, KY, USA

  7. Label-Space Mismatch Distorts Cross-Cohort Evaluation in Breast Cancer Molecular Subtyping

    Oct 18, 2026Suxing Liu, Byungwon Min, Zhijian Zheng +1Cancer Subtype ClassificationCross-Dataset Generalization

    Department of IT Engineering, Mokwon University, Daejeon 35349, Republic of Korea · School of Digital Media Technology, Jiangxi Arts & Ceramics Technology Institute, Jingdezhen 333001, China · University of Alabama, Tuscaloosa, AL 35487, USA +1

  8. Three LiDARs, Twenty-Five Datasets: Cross-Source Generalization in Tree-Species Recognition

    Oct 15, 2026Jae Joong Lee, Bedrich BenesTree Species ClassificationCross-Dataset Generalization

    Purdue University, Department of Computer Science 305 N University St, West Lafayette, IN 47907, USA

  9. From Adults to Children: Benchmarking Foundation Models for Chest X-Ray Classification under Domain Shift

    Oct 15, 2026Sara Inácio, Hugo Proença, João C. NevesMedical Imaging Foundation ModelsChest X-Ray Classification

    University of Beira Interior, Portugal · NOVA LINCS · IT: Instituto de Telecomunicações

  10. Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization

    Oct 9, 2026Xu He, Homayoon BeigiCross-Dataset GeneralizationAudio Classification

    Department of Electrical Engineering Columbia University New York, NY, USA · Mechanical Engineering Dept. and Electrical Engineering Dept. Columbia University, NYC, NY, USA · Recognition Technologies, Inc. South Salem, NY, USA

  11. Dataset-Specific Encoding of Image Content Underlies Cross-Dataset Failure in Brain MRI Foundation Models

    Oct 9, 2026Minh Sao Khue Luu, Bair N. TuchinovMedical Imaging Foundation ModelsMedical Image Representation Learning

    The Artificial Intelligence Research Center of Novosibirsk State University, Novosibirsk 630090, Russia

  12. Cross-dataset harmonization for robust endoscopic image analysis

    Oct 5, 2026Romil Imtiaz, Dimitris K. IakovidisMedical Image AnalysisCross-Dataset Generalization

    Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece

  13. A Data-Centric Review of Plant Disease Datasets: Taxonomy, Critical Analysis, Environmental Variability, and Implications for Precision Agriculture

    Oct 5, 2026Aamir Hilal, Shabir Ahmad Sofi, Neeraj GoelClass-Imbalanced LearningPlant Disease Classification

    Department of Information Technology, National Institute of Technology, Hazratbal Srinagar 190006, Jammu & Kashmir, India · Department of Computer Science and Engineering, Indian Institute of Technology, Ropar Rupnagar 140001, Punjab, India

  14. CCQ: A Multi-State Child Care Quality Dataset to Support AI for Children's Health Research

    Oct 5, 2026Victor Li, Yuzhang Xie, Ziwei Dong +6HealthcareTraining Data Curation

    Emory University, Atlanta, GA, USA

  15. Revisiting the Generalization of Neural Graph Edit Distance Models

    Oct 3, 2026Zhouyang Liu, Ning Liu, Yixin Chen +2Cross-Dataset GeneralizationGraph Matching

    National University of Defense Technology · Information Support Force Engineering University

  16. Bridging Research and Practice: A Systematic Evaluation of Generalist and Dermatology-Specific Models in Clinical Skin Lesion Classification

    Oct 2, 2026Emanoel dos Santos, Kelvin Cunha, Rodrigo Mota +8Skin Lesion ClassificationDermatology

    Centro de Informática, Universidade Federal de Pernambuco (UFPE), Brazil · Hospital das Clinicas, Ebserh, UFPE, Pernambuco, Brazil

  17. GIFTBench: Diagnosing Generalization in Image Forgery Localization and Informing Model Design

    Oct 1, 2026Baoke Dou, Ziye Wang, Hao Wang +5Image Forgery LocalizationCross-Dataset Generalization

  18. Dataset Identity, Not Novelty: The Source of an Inflated OOD Detection Gain

    Oct 1, 2026Donghoon Lee, Shinjin KangDistribution Shift DetectionOOD Detection

    Hongik University

  19. Demistifying Data and Simulator Assumptions in Supervised Causal Discovery

    Sep 29, 2026Pingchuan Ma, Rui Ding, Bojun Huang +1Causal DiscoveryCausal Structure Learning

    Zhejiang University of Technology, China · Microsoft Research Asia · Sony Research +1

  20. Large Language Models for Automated Cross-Domain Machine Learning Task Type Identification: A Benchmark Dataset and Evaluation

    Sep 28, 2026Petros Tsialis, Steffen Limmer, Tobias Rodemann +1LLM EvaluationTabular ML

    University of Applied Sciences Aalen · Honda Research Institute Europe

  21. FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs

    Sep 27, 2026David Restrepo, Chenwei Wu, Luis Filipe Nakayama +4Fairness in Medical Image ClassificationOphthalmic Image Analysis

    CentraleSupélec, Université Paris-Saclay, France · Cancer Data Science Unit, IHU PRISM, Université Paris-Saclay, CentraleSupélec, Gustave Roussy, INSERM, France · University of Michigan, USA +4

  22. Mycelium: A Generalizable Cross-Grid Multi-Task Model for Electrical Distribution Systems

    Sep 27, 2026Zhengyang Wei, Shourya Bose, Helgi Hilmarsson +2Power SystemsMulti-Task Learning

    Stanford University · Pravāh

  23. Bison: Cross-Dataset Learning for Unseen-Compound Perturbation Prediction

    Sep 26, 2026Yunfan Liu, Kasra Ghorbani, Yufei Huang +6Cross-Dataset GeneralizationMolecular Representation Learning

    Zhejiang University · Westlake University · Beihang University +1

  24. Benchmarking Neural Defend ARCAS 1B: A Foundational Multimodal Deepfake Detection Model

    Sep 21, 2026Sivashankar Selvarajan, Piyush Verma, Sumit Kumar +1Deepfake DetectionMultimodal Model Evaluation

    Neural Defend Inc.

  25. Cross-Dataset Generalization of Bangladeshi Rice Leaf Disease Classifiers: Benchmark, Diagnosis, and Mitigation

    Sep 20, 2026Anindya PaulCross-Dataset GeneralizationPlant Disease Classification

    Department of Computer Science and Engineering BRAC University, Dhaka, Bangladesh

  26. Alliance Beats Isolation: Unifying Heterogeneous Allied Datasets Improves Classifier Performance

    Sep 17, 2026Girish Keshav PalshikarCross-Domain Transfer LearningClassification

  27. Cross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification

    Sep 15, 2026Ch Muhammad Awais, Marco Reggiannini, Davide Moroni +1ClassificationCross-Dataset Generalization

    Institute of Science and Technology, National Research Council, Pisa, Italy

  28. Bridging the Gap in ECG-Based Emotion Recognition: A Unified Evaluation of Deep Learning Models

    Sep 14, 2026Timothy C Sweeney-Fanelli, Ajan Ahmed, Masudul ImtiazElectrocardiogram ClassificationEmotion Recognition

    Clarkson University, USA · Affects AI LLC, USA

  29. Domain Generalization for Smartphone-Based Human Activity Recognition: A Systematic Analysis of Components and Interactions

    Sep 14, 2026Otávio Oliveira Napoli, Edson BorinHuman Activity RecognitionDomain Generalization

    Institute of Computing · University of Campinas · Av. Albert Einstein

  30. A Three-Axis Stress Test of LLM vs Classical ML for Network Intrusion Detection under Distribution Shift and Adversarial Evasion

    Sep 11, 2026Muhammad Ebad Atif, Muhammad Haider AliNetwork Intrusion DetectionLLMs for Cybersecurity

    Dhanani School of Science and Engineering Habib University Karachi, Pakistan · Faculty of Computer Sciences and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences Swabi, Pakistan