Search Results for author:
Found 3 papers, 0 papers with code
Pretrained equivariant features improve unsupervised landmark discovery
Locating semantically meaningful landmark points is a crucial component of a large number of computer vision pipelines.
On Data-Augmentation and Consistency-Based Semi-Supervised Learning
Recently proposed consistency-based Semi-Supervised Learning (SSL) methods such as the $\Pi$-model, temporal ensembling, the mean teacher, or the virtual adversarial training, have advanced the state of the art in several SSL tasks.
ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting
Accurate demand forecasts can help on-line retail organizations better plan their supply-chain processes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
