Search Results for author:
Found 3 papers, 2 papers with code
Homeomorphism Alignment for Unsupervised Domain Adaptation
With distribution alignment, it is challenging to acquire a common space which maintains fully the discriminative structure of both domains.
Source-Free Object Detection by Learning To Overlook Domain Style
This approach suffers from both unsatisfactory accuracy of pseudo labels due to the presence of domain shift and limited use of target domain training data.
Disentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation
By this reconstructor, we can construct prototypes for the original features using class prototypes and domain prototypes correspondingly.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
