no code implementations • 28 Mar 2024 • Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, Anjan Dutta
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.
no code implementations • 16 Dec 2021 • Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, S Sumitra
Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed.
1 code implementation • 15 Dec 2019 • Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, Sumitra S
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement.