paper-with-me

홈 › Papers

Is synthetic data from generative models ready for image recognition?

2022-10-14 · Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Song Bai, Xiaojuan Qi

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.

📄 PDF Abstract BibTeX arXiv:2210.07574

Code (1)

cvmi-lab/syntheticdata 공식 구현 pytorch

Tasks

Image GenerationText to Image GenerationText-to-Image GenerationTransfer Learning

Similar Papers 제목 키워드 기반

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images

2023-12-04 · Zhuoran Yu, Chenchen Zhu, Sean Culatana, Raghuraman Krishnamoorthi 외

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+2

Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images

2022-03-18 · Luca Guarnera, Oliver Giudice, Sebastiano Battiato

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 Transfer

SAU: A Dual-Branch Network to Enhance Long-Tailed Recognition via Generative Models

2024-08-29 · Guangxi Li, Yinsheng Song, Mingkai Zheng

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 Classification

Synthetic Iris Presentation Attack using iDCGAN

2017-10-29 · Naman Kohli, Daksha Yadav, Mayank Vatsa, Richa Singh 외

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 Recognition

Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognition

2023-04-30 · Jan Niklas Kolf, Tim Rieber, Jurek Elliesen, Fadi Boutros 외

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