Diffusion-Based Data Augmentation

Latest papers

20 papers6 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Improving Diffusion-Based Augmentation for Data-Scarce Image Classification via Mask-Guided Reference Attention and Repulsive Noise Optimization
Nov 3, 2026Hyun-Jic Oh, GaYeon Koh, Won-Ki JeongDiffusion-Based Data Augmentation Diffusion Sampling
Korea University, Republic of Korea · VIENCE Inc., Republic of Korea
MATS: A Multi-Agent Framework for Controllable and Reflective Tumor Synthesis
Oct 30, 2026Zhongnan Shi, Keyang Zhou, Siyi Li +6Medical Image Synthesis Controllable Image Generation
Fudan University, Shanghai, China · Fudan University Shanghai Cancer Center, Shanghai, China
Uncertainty-Guided Cross-Modal Alignment for Diffusion-Based IoT Intrusion Detection
Oct 29, 2026Mahdi Arab Loodaricheh, Anita Raja, Mohammad Hossein ManshaeiIoT Intrusion Detection Cross-Modal Alignment
Department of Computer Science, Hunter College and The Graduate Center, CUNY, New York, NY, USA
Synthetic Data Augmentation for Functional Data: Wasserstein Risk Bounds and Diffusion-Based Conditional Generation
Oct 25, 2026Yuhao Qi, Wenlin Dai, Xuehu ZhuSynthetic Data Augmentation Data Augmentation
Institute of Statistics and Big Data, Renmin University of China, Beijing, China · School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China
Rethinking Underwater Image Enhancement: Learning through Text-Guided Degradation Curriculum
Oct 21, 2026Hongri Tian, Wenxue Li, Tian Ye +7Underwater Image Enhancement Image Restoration
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China. · China Geological Survey, Beijing, China. · Director of Applied Science, Amazon.com, Inc., U.S.. +1
Local data augmentation for imbalanced binary classification
Oct 19, 2026Harold Gu{é}neau, Alain Celisse, Pascal DelangeClass-Imbalanced Learning Data Augmentation
SAMM · LPP,MODAL
MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement
Oct 17, 2026Ruodai Cui, Shuaizheng Liu, Rongyuan Wu +1Image Enhancement Synthetic Data Augmentation
Department of Computing, The Hong Kong Polytechnic University · Qualcomm Technologies, Inc. · OPPO Research Institute
CoDG-Net: Structure-Guided Style Diffusion and Collaborative Learning to Mitigate Catastrophic Forgetting in Medical Image Domain Generalization
Oct 4, 2026Yucheng Song, Jincan Wang, Haokang Ding +3Data Augmentation Cross-Domain Generalization
School of Computer Science and Engineering, Central South University, Changsha, China · School of Software Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China · College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China
TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification
Aug 31, 2026Ze Chen, Qiming Yu, Zijia Song +2Memory-Augmented Neural Networks Disentangled Representation Learning
National University of Defense Technology Hefei, Anhui, China
Diffuse the object, keep its label: curating detector training data from a few unlabeled photographs via VLM-built 3D vegetation scenes
Aug 10, 2026Mario Malizia, Marnix Enting, Rob Haelterman +1Unsupervised Domain Adaptation Data Augmentation
Royal Military Academy, Brussels, Belgium · KU Leuven, Leuven, Belgium · Flanders Make, Heverlee, Belgium
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
Learning Semantic-Robust Change Detection via Semantic-Invariant Self-Distillation
Jul 21, 2026Jiuhe Qu, Yingping Liang, Ying FuDistribution Shift Robustness Remote Sensing Change Detection
Beijing Institute of Technology, Beijing, China
MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentation
Jun 25, 2026Teerath Kumar, Raja Vavekanand, Muhammad TurabSynthetic Data Augmentation Data Augmentation
School of Computing, Atlantic Technological University, Letterkenny, Ireland. · Department of Information Technology, Benazir Bhutto Shaheed University Lyari, Karachi, 75660, Pakistan. · School of Computing, Dublin City University, Dublin, Ireland.
SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts
Jun 2, 2026Charbel Abi Hana, Tatiana Ghantous, Mikael Khalil +1Data Augmentation Robot Navigation
IDEALworks GmbH · IMT Atlantique · IDEALworks GmbH & Saint Joseph University of Beirut
Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks
May 12, 2026Daniil Dushenev, Nazariy Karpov, Daniil Zinovjev +2Class-Imbalanced Learning Synthetic Data Augmentation
National University of Science and Technology MISIS, Moscow, Russia
Active Tabular Augmentation via Policy-Guided Diffusion Inpainting
May 11, 2026Zheyu Zhang, Shuo Yang, Bardh Prenkaj +1Data Augmentation Tabular Diffusion Models
Technical University of Munich · Munich Center for Machine Learning (MCML)
Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation
Mar 9, 2026Zekun Li, Yinghuan Shi, Yang Gao +1Diffusion-Based Data Augmentation Data Augmentation
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China. · School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR, China.
Generative Spatiotemporal Data Augmentation
Dec 14, 2025Jinfan Zhou, Lixin Luo, Sungmin Eum +2Data Augmentation Synthetic Data Augmentation
University of Chicago · University of Michigan, Ann Arbor · DEVCOM Army Research Laboratory
DiTGaze: Geometry-Conditioned Diffusion Augmentation for Few-Shot Gaze Estimation
Nov 14, 2025Abiram Panchalingam, Indu P. Bodala, Stuart E. MiddletonGaze Estimation Diffusion-Based Data Augmentation
School of Electronics and Computer Science, University of Southampton
ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition
Jun 11, 2025Parsa Rahimi, Sebastien MarcelSynthetic Data Augmentation Synthetic Data Generation
1EPFL, Switzerland · 2Idiap, Switzerland

Nov 3, 2026J/K move · Enter open · S save

Improving Diffusion-Based Augmentation for Data-Scarce Image Classification via Mask-Guided Reference Attention and Repulsive Noise Optimization

Hyun-Jic Oh, GaYeon Koh, Won-Ki Jeong

Korea University, Republic of Korea · VIENCE Inc., Republic of Korea

Diffusion-Based Data Augmentation Diffusion Sampling Few-Shot Image Classification Attention Control in Diffusion Models

Open paper AskPDF arXiv

Diffusion-based data augmentation has emerged as a powerful strategy for addressing data-scarce image classification. Recent pipelines typically adapt a pretrained text-to-image diffusion model to a limited number of class examples and subsequently sample synthetic images using diverse textual prompts. However, in extreme data-scarce regimes such as long-tailed single-sample settings, this approach suffers from a dual failure mode: the generated samples often lack discriminative foreground details crucial for classifier training, and the adapted class prior can bias the early denoising process, causing output images to exhibit similar patterns despite varying text prompts. To overcome these limitations, we propose a sampling-side framework of two complementary components that simultaneously enhance fine details and diversity. First, Mask-Guided Reference (MGR) Attention updates only foreground value tokens with reference features via zero-shot segmentation, limiting reference influence to the target object and mitigating excessive global feature injection. Second, Repulsive Noise Optimization (RNO) encourages initial noise trajectories to diverge from dominant generative modes of the adapted model, enabling target prompts to express broader contextual variation. Extensive evaluations show consistent improvements, with the largest gains in long-tailed single-sample settings of up to 2.50 and 2.94 points on CUB-LT IF100, and further robustness across few-shot and background-shift evaluations.