Is synthetic data from generative models ready for image recognition?
Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images. Though the results are astonishing to human eyes, how applicable these generated images are for recognition tasks remains under-explored. In this work, we extensively study whether and how synthetic images generated from state-of-the-art text-to-image generation models can be used for image recognition tasks, and focus on two perspectives: synthetic data for improving classification models in data-scarce settings (i.e. zero-shot and few-shot), and synthetic data for large-scale model pre-training for transfer learning. We showcase the powerfulness and shortcomings of synthetic data from existing generative models, and propose strategies for better applying synthetic data for recognition tasks. Code: https://github.com/CVMI-Lab/SyntheticData.
Code (1)
Tasks
Image GenerationText to Image GenerationText-to-Image GenerationTransfer LearningSimilar Papers 제목 키워드 기반
Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images
Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generatin…
DiversityDomain AdaptationDomain GeneralizationImage Generation+2Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images
Most recent style-transfer techniques based on generative architectures are able to obtain synthetic multimedia contents, or commonly called deepfakes, with almost no artifacts. Researchers already demonstrated that synt…
Face SwappingStyle TransferSAU: A Dual-Branch Network to Enhance Long-Tailed Recognition via Generative Models
Long-tailed distributions in image recognition pose a considerable challenge due to the severe imbalance between a few dominant classes with numerous examples and many minority classes with few samples. Recently, the use…
image-classificationImage ClassificationSynthetic Iris Presentation Attack using iDCGAN
Reliability and accuracy of iris biometric modality has prompted its large-scale deployment for critical applications such as border control and national ID projects. The extensive growth of iris recognition systems has …
Generative Adversarial NetworkIris RecognitionIdentity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognition
Many of the commonly used datasets for face recognition development are collected from the internet without proper user consent. Due to the increasing focus on privacy in the social and legal frameworks, the use and dist…
Face RecognitionGenerative Adversarial NetworkSynthetic Face Recognition