-
Semi-supervised Semantic Segmentation with Error Localization Network
Semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. -
GENERALIZING SKILLS WITH SEMI-SUPERVISED REINFORCEMENT LEARNING
Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to... -
Self-supervised and semi-supervised learning for GANs
Self-supervised and semi-supervised learning for GANs -
Semi-supervised conditional GANs
Semi-supervised conditional GANs -
High-Fidelity Image Generation With Fewer Labels
High-fidelity image generation with fewer labels -
Virtual Adversarial Training
The authors used MNIST, SVHN, and CIFAR10 datasets for their experiments.
