Search Results for author:
Found 3 papers, 1 papers with code
DeNetDM: Debiasing by Network Depth Modulation
Current approaches to address such biases typically involve utilizing bias annotations, reweighting based on pseudo-bias labels, or enhancing diversity within bias-conflicting data points through augmentation techniques.
Self-supervised Enhancement of Latent Discovery in GANs
Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed.
Disentanglement based Active Learning
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
