Zero Shot Learning via Multi-Scale Manifold Regularization

Shay Deutsch; Soheil Kolouri; Kyungnam Kim; Yuri Owechko; Stefano Soatto

CVPR 2017poster50 citations

Zero Shot Learning via Multi-Scale Manifold Regularization

Shay Deutsch, Soheil Kolouri, Kyungnam Kim, Yuri Owechko, Stefano Soatto

Abstract

We address zero-shot learning using a new manifold alignment framework based on a localized multi-scale transform on graphs. Our inference approach includes a smoothness criterion for a function mapping nodes on a graph (visual representation) onto a linear space (semantic representation), which we optimize using multi-scale graph wavelets. The robustness of the ensuing scheme allows us to operate with automatically generated semantic annotations, resulting in an algorithm that is entirely free of manual supervision, and yet improves the state-of-the-art as measured on benchmark datasets.

BibTeX

@inproceedings{cvpr2017_zeroshotlearning,
  title = {Zero Shot Learning via Multi-Scale Manifold Regularization},
  author = {Shay Deutsch and Soheil Kolouri and Kyungnam Kim and Yuri Owechko and Stefano Soatto},
  booktitle = {CVPR 2017},
  year = {2017}
}