Survey of synthetic data augmentation in computer vision
Survey of synthetic data augmentation in computer vision
A survey of synthetic data augmentation methods in computer vision
arXiv paper abstract https://arxiv.org/abs/2403.10075
arXIv PDF paper https://arxiv.org/pdf/2403.10075.pdf
... approach to tackling computer vision problems is to train deep convolutional neural network (CNN) models using large-scale image datasets which are representative of the target task.
... where data for the target domain is not accessible, a viable workaround is to synthesize training data from scratch--i.e., synthetic data augmentation.
This paper presents an extensive review of synthetic data augmentation techniques.
It covers data synthesis approaches based on realistic 3D graphics modeling, neural style transfer (NST), differential neural rendering, and generative artificial intelligence (AI) techniques such as generative adversarial networks (GANs) and variational autoencoders (VAEs).
For ... these ... methods, ... focus on ... data generation and augmentation techniques, ... scope of application and ... use-cases, as well as ... limitations and ... workarounds.
... provide a summary of ... synthetic datasets for training ... vision models, highlighting ... features, application domains and ... tasks ... discuss the effectiveness of ... augmentation methods ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comentarios