← Search

Tony Han

2 accepted papers

2017

Learning Efficient Object Detection Models with Knowledge Distillation

NeurIPS 2017poster

Despite significant accuracy improvement in convolutional neural networks (CNN) based object detectors, they often require prohibitive runtimes to process an image for real-time applications. State-of-the-art models often use very deep networks with a large number of floating point operations. Effor…

Cited by 1342SourcePDFScholar
2016

Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

ICML 2016poster

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of s…