Search Results for author:
Found 1 papers, 1 papers with code
Gradient Aligned Regression via Pairwise Losses
In this work, we propose GAR (Gradient Aligned Regression) as a competitive alternative method in label space, which is constituted by a conventional regression loss and two pairwise label difference losses for gradient alignment including magnitude and direction.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
