Overview

Data augmentation creates modified or synthetic training examples so models can learn from limited, imbalanced, or varied data. Common approaches include geometric and appearance transforms, Mixup and CutMix, graph and feature perturbations, and examples generated with diffusion models, language models, or simulation. Recent work increasingly adapts augmentation to a model’s learning state and to domain-specific constraints in settings such as medical imaging, speech, and robotics. The central tension is to add useful diversity without changing labels or important structure; effectiveness depends on the task and should be tested for out-of-domain performance, calibration, and synthetic-data quality as well as accuracy.

Latest papers

CardsList

273 papers29 papers in the last four weeks, up 16% on the four weeks before. 0.2% of all new papers.

  1. Isotropic Embedding Perturbations for Robust Vision Language Encoders

    Sep 9, 2026Hyesong Choi, Daeun Kim, Song Park +5VLM RobustnessData Augmentation

  2. Sparse Data Augmentation for Optimization with Provable Guarantees

    Sep 8, 2026Behrooz Tahmasebi, Melanie WeberData AugmentationNonconvex Optimization

  3. From Masking to Merging: Rethinking SpecAugment for Efficient Audio Spectrogram Transformer

    Sep 6, 2026Minhee Park, Hyowon Ahn, Chanwoo KimToken MergingData Augmentation

  4. An Analysis of Self-supervised Pre-training with Dependent Samples

    Sep 4, 2026Maximilian Fleissner, Debarghya Ghoshdastidar, Samory KpotufeSelf-Supervised LearningSelf-Supervised Pre-Training

  5. Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views

    Sep 3, 2026Joseph Lee, Yidi Huang, Dokyoon Kim +2Language Model PretrainingData Augmentation

  6. Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations

    Sep 3, 2026Onat Şahin, Mohammad Altillawi, George Eskandar +23D Gaussian SplattingData Augmentation

  7. Generalizable Brain Tumor Segmentation with Self-Training and Tumor-Aware Deformations

    Sep 2, 2026Henrique Zan Grande, Jeovane Honorio Alves, Rayson Laroca +1Brain Tumor SegmentationBraTS

  8. Statistical Feature Augmentation for Anomaly Detection in Dynamic Graphs

    Sep 2, 2026Philipp Schlinge, Jean-Luc Schnipper, Martin AtzmuellerTemporal GNNsData Augmentation

  9. SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling

    Aug 31, 2026Chad Wong, Sicheng Chen, Tianyi Zhang +4Data AugmentationHistopathology Image Classification

  10. Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification

    Aug 31, 2026Chuanhang Qiu, Yanran Xu, Yue Wang +1Class-Imbalanced LearningData Augmentation

  11. ActiveAugment: Online Active Learning for Augmentation Selection in Deep Learning

    Aug 28, 2026Noah Videcrantz, Mostafa Mehdipour GhaziData AugmentationActive Learning

  12. Cross-Spectral Dense Correspondence for Multimodal Spectral Medical Imaging

    Aug 28, 2026Eric L. Wisotzky, Jost Triller, Simon W. Härtl +3Image MatchingCross-Modal Feature Matching

  13. Image Augmentation as Test Generation for Deep Learning-Based Image Retrieval Systems

    Aug 27, 2026Yehan De Silva, Anirudh Sridhar, Armin Lotfy +6Data AugmentationImage Retrieval

  14. Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic Segmentation

    Aug 26, 2026Olasimbo Ayodeji Arigbabu, Abimbola Ismail ArigbabuData AugmentationSemantic Segmentation

  15. Improving Cross-Site Whole-Heart Segmentation

    Aug 25, 2026Tanish Mudaliar, Justin Li, Daniel Lin +4Medical Image Segmentation3D Medical Image Segmentation

  16. Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection

    Aug 25, 2026Long Hoang Pham, Quoc Pham-Nam Ho, Huy-Hung Nguyen +10Object DetectionDomain Generalization

  17. Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation

    Aug 24, 2026Dexter Wen Jie Teo, Kumaradevan PunithakumarMedical Image Segmentation3D Medical Image Segmentation

  18. Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data

    Aug 24, 2026Yifei Song, Kun Efimov-Zhang, Claire GardentText GenerationCross-Domain Transfer Learning

  19. Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching

    Aug 19, 2026Sebastian Doerrich, Francesco Di Salvo, Shyam Nandan Rai +2Data AugmentationDomain Generalization

  20. The Impact of CutMix on Reliability and Robustness in Semantic Segmentation

    Aug 19, 2026Steven Landgraf, Markus UlrichSemantic SegmentationData Augmentation

  21. GATTA: Graph Active Learning with Test-Time Augmentation

    Aug 15, 2026Zsombor Bánfi, András Gézsi, András FormanekGraph Data AugmentationActive Learning

  22. Boosting Data Augmentation with Stochastic Weight Averaging

    Aug 14, 2026Longde Huang, Axel Flinth, Jan E. GerkenData AugmentationEquivariant Representation Learning

  23. FISSION: Label Augmentation for Bot Detection

    Aug 14, 2026Sen Yang, Ignacy Nieweglowski, Aviv YaishSocial Bot DetectionData Augmentation

  24. Simulation-Driven Vehicular Traffic Data Augmentation: Extending Sensor Coverage Through Virtual Sensing

    Aug 14, 2026Davide Andrea Guastella, Eladio Montero Porras, Evangelos Pournaras +1Data AugmentationSynthetic Data Augmentation

  25. TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement

    Aug 12, 2026Karim Aly, Alexei Sharpanskykh, Jacco HoekstraData AugmentationSynthetic Tabular Data Generation