Synthetic Data Augmentation

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 85% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 294

All topics

SynThermFace: Amplifying Limited Paired Data for Visible-Thermal Face Recognition via Synthetic Data Generation
Sep 9, 2026Anjith George, Adam Unal, Sebastien MarcelThermal Imaging Synthetic Data Augmentation
Idiap Research Institute Rue Marconi 19 Martigny, Switzerland · University of Lausanne (UNIL) Lausanne, Switzerland
Compensating for Scarce Historical Images in Cross-Domain Cultural Heritage Retrieval Using Synthetic Aging
Sep 8, 2026Marcin Iwanowski, Adam Mazgaj, Ferdynand Gorski +1Synthetic-to-Real Domain Adaptation Synthetic Data Augmentation
Inst.of Engineering and Technology, Faculty of Physics, Astronomy and Informatics, Nicolaus Copernicus University, ul.Grudziądzka 5, 87-100 Toruń, POLAND · Clemens, ul.Pawlikowskiego 10/2, 31-127 Krakow, POLAND · cClemens, ul.Pawlikowskiego 10/2, 31-127 Krakow, POLAND +1
The Impact of Synthetic Data Augmentation on Discourse-Pragmatic Function Classification
Sep 3, 2026Sara Sorahi, Kevin Tang, Reza KazemianSynthetic Data Augmentation Synthetic Data Generation
Faculty of Arts and Humanities, Heinrich Heine University Düsseldorf · Institute of Linguistics · Department of English Language and Linguistics +2
Domain shift-robust object detection with GenAI image editing
Sep 2, 2026Isabel D. Stein, Thijs A. Eker, Sebastiaan P. Snel +4Object Detection Domain Generalization
TNO - Defence, Security and Safety, the Hague, the Netherlands · Radboud University, Nijmegen, the Netherlands
On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study
Sep 1, 2026Chathurika S Abeykoon, Mathias Nthiani Muia, Mallory GoldsteinClass-Imbalanced Learning Synthetic Data Augmentation
SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations
Sep 1, 2026Yiming Luo, Rongqiang Zhao, Jie LiuDistribution Shift Robustness Synthetic Data Augmentation
1Harbin Institute of Technology · 2State Key Laboratory of Smart Farm Technologies and Systems
LISynSeg: Data-Centric Label-to-Image Synthesis for Cross-Modality Whole-Heart Segmentation
Aug 31, 2026Jiacheng Wang, Ivana Isgum, Ipek OguzCross-Modality Medical Image Segmentation Synthetic Data Augmentation
Vanderbilt University, Nashville, TN, USA · Mayo Clinic, Rochester, MN, USA
Identity-Conditioned Latent Consistency Distillation for Face Synthesis
Aug 31, 2026Tiago Kienen Chaves, Bernardo Biesseck, David MenottiSynthetic Data Augmentation Latent Diffusion Models
Department of Informatics, Federal University of Paraná, Curitiba, Brazil · Federal Institute of Mato Grosso (IFMT), Pontes e Lacerda, MT, Brazil
RailGen: Improving Railway Intrusion Detection via Agent-Guided Small-Scale Foreign Object Generation
Aug 31, 2026Quan Hao, Ziyang Tao, Chenxi Zhang +3Synthetic Data Augmentation Small Object Detection
School of Information Science and Technology, Beijing University of Technology, Beijing, China · College of Computer Science, Beijing University of Technology, Beijing, China · Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing 100190, China
RailSyn: Diagnosis-Guided Image Generation for Traceable Data Completion in Railway Foreign Object Detection
Aug 31, 2026Quan Hao, Chenxi Zhang, Ziyang Tao +6Synthetic Data Augmentation Synthetic Data Generation
1The School of Information Science and Technology, Beijing University of Technology · 2Pratt School of Engineering, Duke University · 3Academy of Mathematics and Systems Science, Chinese Academy of Sciences +3
AIA $^{2}$ : Attribute-Agnostic Imbalance Augmentation for Subgroup Robustness
Aug 31, 2026Hanshu Rao, Guangzeng Han, Xiaolei HuangClass-Imbalanced Learning Synthetic Data Augmentation
University of Memphis · University of Missouri
GraM-Diff: A Unified Graph-Mamba Diffusion Framework for EEG-Based Alzheimer's Disease Data Generation and Diagnosis
Aug 30, 2026M. Tanveer, Ayush Singh Rana, Sanskriti Jain +5Synthetic Data Augmentation Electroencephalography
Indian Institute of Technology Indore, Indore 453552, Madhya Pradesh, India
Phoneme-guided TTS augmentation for ASR: A unified pipeline and multilingual evaluation
Aug 27, 2026Zhen Wang, TianRui Wu, RongQi Han +3Synthetic Data Augmentation TTS Synthesis
Shanghai Qi Zhi Institute, Shanghai, China · Megatronix (Beijing) Technology Co., Ltd. · Tsinghua University, Beijing, China
Physics-informed Diffusion Generative Model for Time-Series Data Synthesis in Dynamic Systems
Aug 11, 2026Haiteng Wang, Yunfei Zhu, Tao Wang +4Synthetic Data Augmentation Synthetic Data Generation
School of Automation Science and Electrical Engineering, Beihang University, Beijing, 100191, China. · School of Software, Beihang University, Beijing, 100191, China. · Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, 100191, Hong Kong. +1
Training Set Synthesis for Bioacoustic Denoising: A Case Study With Mice
Aug 10, 2026Reyhaneh Abbasi, Peter Balazs, Vincent Lostanlen +4Synthetic Data Augmentation Bioacoustics
Acoustics Research Institute of the Austrian Academy of Sciences, Vienna, Austria · Vienna Doctoral School of Cognition, Behavior, and Neuroscience, University of Vienna, Vienna, Austria · Interdisciplinary Transformation University Austria (IT:U), Linz, Austria +3
Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gap
Aug 6, 2026Luis S. Luevano, Ünsal Öztürk, Hatef Otroshi Shahreza +2Synthetic Data Augmentation Synthetic Data Generation
Idiap Research Institute, Switzerland
OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations
Aug 6, 2026Robin Trombetta, Carole LartizienSynthetic Data Augmentation Medical Image Segmentation
Univ. Lyon, CNRS UMR 5220, Inserm U1294, INSA Lyon, UCBL, CREATIS, France
A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasets
Aug 5, 2026Harvey Mannering, Yilin Zhang, Ziao Liu +3Synthetic Data Augmentation Ultrasound Imaging
University of Southampton · Tsinghua University · King’s College London +1
Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction
Aug 5, 2026Quinn Ledingham, Zhengsen Xu, Yimin Zhu +6Synthetic Data Augmentation Tabular Prediction
Department of Geomatics Engineering, University of Calgary, Calgary, AB, Canada
Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection
Aug 5, 2026Zijian Zhuang, Yixiong Zou, Yuhua Li +1Synthetic Data Augmentation Data Augmentation
School of Computer Science and Technology, Huazhong University of Science and Technology, China
FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis
Aug 4, 2026Zhang Weihui, Wang Ruizhi, Xu Hongye +3Physics-Informed Generative Modeling Synthetic Data Augmentation
Zhejiang University, Zhejiang, China
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
Aug 4, 2026Chunyang Jiang, Pingping Zhang, Yuzhi Zhao +9Synthetic Data Augmentation Data Augmentation
Hong Kong University of Science and Technology · City University of Hong Kong · Chinese University of Hong Kong
Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection
Aug 2, 2026Linhai Zhuo, Junxi Cai, Tianwen Qian +2Synthetic Data Augmentation Few-Shot Domain Adaptation
Fuzhou University · East China Normal University · Xiamen University +1
Entity-Faithful Repair of Synthetic Supervision for Zero-Shot Image Captioning
Aug 2, 2026Zhiyue Liu, Wenkai Zhou, Jian Qin +1Synthetic Data Augmentation Image Captioning
School of Computer, Electronics and Information Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning, Guangxi, China
Impact of Dataset Composition on Embedded Real-Time UAV Wildfire Detection Using Compact YOLO Models
Aug 1, 2026Eduardo de los Santos, Andre S. Kelbouscas, Ricardo B. Grando +1Synthetic Data Augmentation Wildfire Detection
Robotics and AI Lab, Technological University of Uruguay, Rivera, Uruguay
DualDiT: A Conditional Dual-Output Diffusion Transformer for Joint OCT Image and Segmentation Mask Generation
Jul 31, 2026Fernando García-Torres, Rocío del Amor, Sandra Morales +4Synthetic Data Augmentation Diffusion Transformer
Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano (HUMAN-tech), Universitat Politècnica de València, Camino de Vera, s/n, Valencia, 46022, Comunidad Valenciana, Spain · Artikode Intelligence S.L, Camino de Vera, s/n, Valencia, 46022, Comunidad Valenciana, Spain · Biomedical Technology Center of the Medical Faculty, University of Muenster, Mendelstraße 17, Münster, 48149, North Rhine-Westphalia, Germany +1
Can Synthetic Data Overcome the Generalization Limits of AI-Based Flower and Pod Detection Across Cowpea Breeding Genotypes and Environments?
Jul 30, 2026Hamid Kamangir, Jonathan Berlingeri, Earl Ranario +6Synthetic-to-Real Domain Adaptation Synthetic Data Augmentation
Department of Biological and Agricultural Engineering, University of California Davis, Davis, CA, USA. · Department of Plant Science, University of California Davis, Davis, CA, USA.
Towards Autonomous Aircraft Surveillance from Nanosatellites through On-Board Inference and Generative Data Augmentation
Jul 30, 2026Antonio Delgado-Rosa, David Muñoz-Valero, Enrique Adrian Villarrubia-Martin +1Synthetic Data Augmentation Remote Sensing
Escuela de Ingeniería Industrial y Aeroespacial de Toledo, Department of Technologies and Information Systems, Universidad de Castilla–La Mancha, Avenida Carlos III, s/n, Toledo, 45071, Spain · Escuela Superior de Informática, Department of Technologies and Information Systems, Universidad de Castilla-La Mancha, Paseo de la Universidad 4, Ciudad Real, 13071, Spain
Object Detection for Autonomous Driving in Chinese Rural Scenes: An Experimental Study on Real-Synthetic Data Mixing and Model Evaluation
Jul 29, 2026Danning Zhu, Ziyan Lin, Jing WuAutonomous Driving Datasets Autonomous Driving Benchmarks
Wuhan University of Technology Wuhan, China
A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar
Jul 26, 2026C. J. Moore, Gregory D. Vetaw, Jordan MalofSynthetic Data Augmentation Data Augmentation
University of Missouri, Columbia, Missouri, USA · Naval Surface Warfare Center Panama City Division, Panama City, Florida, USA

Sep 9, 2026, cs.CVJ/K move · Enter open · S save

SynThermFace: Amplifying Limited Paired Data for Visible-Thermal Face Recognition via Synthetic Data Generation

Anjith George, Adam Unal, Sebastien Marcel

Idiap Research Institute Rue Marconi 19 Martigny, Switzerland · University of Lausanne (UNIL) Lausanne, Switzerland

Thermal Imaging Synthetic Data Augmentation Face Recognition

Open paper AskPDF arXiv

Face recognition (FR) is a widely used modality for biometric authentication, but conventional models rely on visible-spectrum imagery and degrade when high-quality RGB images cannot be captured. Cross-spectral face recognition addresses this limitation by matching visible images with other modalities such as thermal imagery, enabling more reliable performance in low-light, nighttime, and unconstrained conditions. However, progress is limited by the scarcity of paired visible-thermal data, which is difficult and costly to collect at scale. We propose SynThermFace, a framework that amplifies limited real visible-thermal supervision into larger paired adaptation datasets for cross-spectral face recognition. A diffusion model is first adapted using a limited set of paired visible--thermal images and then used to generate large-scale paired visible--synthetic thermal data from existing real or synthetic visible face datasets. The generated pairs are used to adapt a pretrained visible-spectrum face recognition model into a CFR model. Unlike synthesis-based approaches that require image translation at test time, the proposed method shifts generation to the training stage and performs inference with a single forward pass through the adapted recognition model. Under the same MCXFace real-pair protocol, PACT improves over the evaluated CFR adaptation baselines, isolating the effect of the proposed adaptation objective. Training PACT on larger generated paired datasets provides additional improvements over both the unadapted model and the real-pair PACT configuration. Cross-database evaluation on the Tufts dataset provides evidence that the learned representation transfers to an unseen database. The source code and trained models will be made publicly available.

Momentum

Related topics

Latest papers 294