Search Results for author:
Found 4 papers, 1 papers with code
A Fourier Transform Framework for Domain Adaptation
By using unsupervised domain adaptation (UDA), knowledge can be transferred from a label-rich source domain to a target domain that contains relevant information but lacks labels.
IF2Net: Innately Forgetting-Free Networks for Continual Learning
Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge.
MixDehazeNet : Mix Structure Block For Image Dehazing Network
For example, compared with the previous state-of-the-art methods, MixDehazeNet achieves a significant improvement (42. 62dB PSNR) on the SOTS indoor dataset.
Ranked #1 on
Image Dehazing
on Haze4k
Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
Such three strategies are formulated into a unified framework to address the fairness issue and domain shift challenge.
