← Search

Ken Kansky

2 accepted papers

2017

Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics

ICML 2017poster

The recent adaptation of deep neural network-based methods to reinforcement learning and planning domains has yielded remarkable progress on individual tasks. Nonetheless, progress on task-to-task transfer remains limited. In pursuit of efficient and robust generalization, we introduce the Schema Ne…

Cited by 300SourcePDFScholar
2016

Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data

NeurIPS 2016poster

We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative methods. In addition to transcribing text from challenging images,…

Cited by 13SourcePDFScholar