
-
Self-Supervised Pretraining Improves Self-Supervised Pretraining
While self-supervised pretraining has proven beneficial for many compute...
read it
-
Minimax Active Learning
Active learning aims to develop label-efficient algorithms by querying t...
read it
-
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
The goal of continual learning (CL) is to learn a sequence of tasks with...
read it
-
Adversarial Continual Learning
Continual learning aims to learn new tasks without forgetting previously...
read it
-
WiCV 2019: The Sixth Women In Computer Vision Workshop
In this paper we present the Women in Computer Vision Workshop - WiCV 20...
read it
-
Uncertainty-guided Continual Learning with Bayesian Neural Networks
Continual learning aims to learn new tasks without forgetting previously...
read it
-
Variational Adversarial Active Learning
Active learning aims to develop label-efficient algorithms by sampling t...
read it
-
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Many approaches in generalized zero-shot learning rely on cross-modal ma...
read it
-
Compositional GAN: Learning Conditional Image Composition
Generative Adversarial Networks (GANs) can produce images of surprising ...
read it
-
Gradient-free Policy Architecture Search and Adaptation
We develop a method for policy architecture search and adaptation via gr...
read it