Effective Data Augmentation With Diffusion Models
Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data augmentation combines simple transformations like rotations and flips to generate new images from existing ones. However, these new images lack diversity along key semantic axes present in the data. Current augmentations cannot alter the high-level semantic attributes, such as animal species present in a scene, to enhance the diversity of data. We address the lack of diversity in data augmentation with image-to-image transformations parameterized by pre-trained text-to-image diffusion models. Our method edits images to change their semantics using an off-the-shelf diffusion model, and generalizes to novel visual concepts from a few labelled examples. We evaluate our approach on few-shot image classification tasks, and on a real-world weed recognition task, and observe an improvement in accuracy in tested domains.
Code (1)
Tasks
Data AugmentationDiversityFew-Shot Image Classificationimage-classificationImage ClassificationRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustness. Applying DiffAug to a given example c…
DenoisingImage GenerationOut-of-Distribution DetectionHybrid Diffusion Model for Breast Ultrasound Image Augmentation
We propose a hybrid diffusion-based augmentation framework to overcome the critical challenge of ultrasound data augmentation in breast ultrasound (BUS) datasets. Unlike conventional diffusion-based augmentations, our ap…
Text-to-Image GenerationImage AugmentationData AugmentationScore Augmentation for Diffusion Models
Diffusion models have achieved remarkable success in generative modeling. However, this study confirms the existence of overfitting in diffusion model training, particularly in data-limited regimes. To address this chall…
Data AugmentationDataset Augmentation by Mixing Visual Concepts
This paper proposes a dataset augmentation method by fine-tuning pre-trained diffusion models. Generating images using a pre-trained diffusion model with textual conditioning often results in domain discrepancy between r…
Image CaptioningErase, then Redraw: A Novel Data Augmentation Approach for Free Space Detection Using Diffusion Model
Data augmentation is one of the most common tools in deep learning, underpinning many recent advances including tasks such as classification, detection, and semantic segmentation. The standard approach to data augmentati…
Data AugmentationDiversitySemantic Segmentation