Skip to yearly menu bar Skip to main content


Poster

Unsupervised Transformation Learning via Convex Relaxations

Tatsunori Hashimoto · Percy Liang · John Duchi

Pacific Ballroom #15

Keywords: [ Unsupervised Learning ] [ Nonlinear Dimensionality Reduction and Manifold Learning ] [ Representation Learning ]


Abstract:

Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait. We propose an unsupervised approach to learn such transformations by attempting to reconstruct an image from a linear combination of transformations of its nearest neighbors. On handwritten digits and celebrity portraits, we show that even with linear transformations, our method generates visually high-quality modified images. Moreover, since our method is semiparametric and does not model the data distribution, the learned transformations extrapolate off the training data and can be applied to new types of images.

Live content is unavailable. Log in and register to view live content