← Search

Qianfen Jiao

2 accepted papers

2021

High Fidelity GAN Inversion via Prior Multi-Subspace Feature Composition

AAAI 2021technical

Generative Adversarial Networks (GANs) have shown impressive gains in image synthesis. GAN inversion was recently studied to understand and utilize the knowledge it learns, where a real image is inverted back to a latent code and can thus be reconstructed by the generator. Although increasing the nu…

Cited by 0SourcePDFScholar
2020

Model Adaptation: Unsupervised Domain Adaptation Without Source Data

CVPR 2020poster

In this paper, we investigate a challenging unsupervised domain adaptation setting --- unsupervised model adaptation. We aim to explore how to rely only on unlabeled target data to improve performance of an existing source prediction model on the target domain, since labeled source data may not be a…

Cited by 0PDFScholar