1S-DAug: One-Shot Data Augmentation for Robust Few-Shot Generalization

2026-01-27 · Yunwei Bai, Ying Kiat Tan, Yao Shu, Tsuhan Chen arxiv

Few-shot learning (FSL) challenges model generalization to novel classes based on just a few shots of labeled examples, a testbed where traditional test-time augmentations fail to be effective. We introduce 1S-DAug, a one-shot generative augmentation operator that synthesizes diverse yet faithful variants from just one example image at test time. 1S-DAug couples traditional geometric perturbations with controlled noise injection and a denoising diffusion process conditioned on the original image. The generated images are then encoded and aggregated, alongside the original image, into a combined representation for more robust few-shot predictions. Integrated as a training-free model-agnostic plugin, 1S-DAug consistently improves few-shot classification across standard benchmarks of 4 different datasets without any model parameter update, including achieving up to 20\% relative accuracy improvement on the miniImagenet 5-way-1-shot benchmark. Additionally, we provide extension experiments on the larger vision language models as well as theoretical analyses.

📄 PDF Abstract BibTeX arXiv:2602.00114

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Learning Data Augmentation

When to Learn What: Model-Adaptive Data Augmentation Curriculum

2023-09-09 · ICCV 2023 1 · Chengkai Hou, Jieyu Zhang, Tianyi Zhou

Data augmentation (DA) is widely used to improve the generalization of neural networks by enforcing the invariances and symmetries to pre-defined transformations applied to input data. However, a fixed augmentation polic…

Data Augmentation Fairness image-classification Image Classification

LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation

2025-05-26 · Piyush Tiwary, Kinjawl Bhattacharyya, Prathosh A. P

Medical image segmentation models often struggle to generalize across different domains due to various reasons. Domain Generalization (DG) methods overcome this either through representation learning or data augmentation…

Data Augmentation Domain Generalization Image Segmentation Medical Image Segmentation+3

HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness

2023-07-21 · ICCV 2023 1 · Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu

Convolutional Neural Networks (CNN) are known to exhibit poor generalization performance under distribution shifts. Their generalization have been studied extensively, and one line of work approaches the problem from a f…

Adversarial Robustness Data Augmentation model Out-of-Distribution Detection

Generative Data Augmentation for Commonsense Reasoning

2020-04-24 · Findings of the Association for Computational Linguistics 2020 · Yiben Yang, Chaitanya Malaviya, Jared Fernandez, Swabha Swayamdipta 외

Recent advances in commonsense reasoning depend on large-scale human-annotated training data to achieve peak performance. However, manual curation of training examples is expensive and has been shown to introduce annotat…

Common Sense Reasoning Coreference Resolution Data Augmentation Out-of-Distribution Generalization+3

Tied-Augment: Controlling Representation Similarity Improves Data Augmentation

2023-05-22 · Emirhan Kurtulus, Zichao Li, Yann Dauphin, Ekin Dogus Cubuk

Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and superv…

Data Augmentation