Tagger: Deep Unsupervised Perceptual Grouping

  title={Tagger: Deep Unsupervised Perceptual Grouping},
  author={Klaus Greff and Antti Rasmus and Mathias Berglund and Tele Hotloo Hao and J{\"u}rgen Schmidhuber and Harri Valpola},
We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an unsupervised manner or alongside any supervised task. We enable a neural network to group the representations of different objects in an iterative manner through a differentiable mechanism. We achieve very fast convergence by allowing the system to amortize the… CONTINUE READING
This paper has been referenced on Twitter 67 times. VIEW TWEETS


Publications citing this paper.

58 Citations

Citations per Year
Semantic Scholar estimates that this publication has 58 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…