R
Rich Zemel
Researcher at University of Toronto
Publications - 6
Citations - 8696
Rich Zemel is an academic researcher from University of Toronto. The author has contributed to research in topics: Image segmentation & Graph (abstract data type). The author has an hindex of 6, co-authored 6 publications receiving 6917 citations. Previous affiliations of Rich Zemel include Canadian Institute for Advanced Research.
Papers
More filters
Proceedings Article
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Kelvin Xu,Jimmy Ba,Ryan Kiros,Kyunghyun Cho,Aaron Courville,Ruslan Salakhudinov,Ruslan Salakhudinov,Rich Zemel,Rich Zemel,Yoshua Bengio,Yoshua Bengio +10 more
TL;DR: An attention based model that automatically learns to describe the content of images is introduced that can be trained in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound.
Proceedings Article
Learning Fair Representations
TL;DR: A learning algorithm for fair classification that achieves both group fairness (the proportion of members in a protected group receiving positive classification is identical to the proportion in the population as a whole), and individual fairness (similar individuals should be treated similarly).
Proceedings Article
Multimodal Neural Language Models
TL;DR: This work introduces two multimodal neural language models: models of natural language that can be conditioned on other modalities and imagetext modelling, which can generate sentence descriptions for images without the use of templates, structured prediction, and/or syntactic trees.
Proceedings Article
Stochastic k-Neighborhood Selection for Supervised and Unsupervised Learning
TL;DR: KNCA is presented, which generalizes NCA by learning distance metrics that are appropriate for kNN with arbitrary k, and shows that kNCA often improves classification accuracy over state of the art methods, produces qualitative differences in the embeddings as k is varied, and is more robust with respect to label noise.
Proceedings Article
High Order Regularization for Semi-Supervised Learning of Structured Output Problems
Yujia Li,Rich Zemel,Rich Zemel +2 more
TL;DR: A new max-margin framework for semi-supervised structured output learning is proposed, that allows the use of powerful discrete optimization algorithms and high order regularizers defined directly on model predictions for the unlabeled examples.