[AI Seminar] AI Lunch -- Hsiao-Yu Tung -- April 4
Adams Wei Yu
weiyu at cs.cmu.edu
Tue Apr 4 10:40:24 EDT 2017
A reminder that the talk is today (Tuesday) noon.
On Sun, Apr 2, 2017 at 2:04 PM, Adams Wei Yu <weiyu at cs.cmu.edu> wrote:
> Dear faculty and students,
> We look forward to seeing you Next Tuesday, April 4, at noon in NSH 3305
> for AI lunch. To learn more about the seminar and lunch, please visit the
> AI Lunch webpage <http://www.cs.cmu.edu/~aiseminar/>.
> On Tuesday, Hsiao-Yu Tung <https://sfish0101.bitbucket.io/> will give the
> following talk:
> Title: Adversarial Inversion: Self-supervision with Adversarial Priors.
> We as humans form explanations of visual observations in terms of familiar
> concepts and memories that are used to interpret and complete information
> of the image pixels. Computer Vision researchers have developed excellent
> methods that learn a direct mapping from images to desired outputs
> using human annotations or synthetically generated data. Despite their
> success, such supervised models very much depend on the amount of
> annotated data available, a gap we seek to address.
> In this talks, we introduce adversarial inversion, a weakly supervised
> neural network model that combines self-supervision with adversarial
> constraints. Given visual input, our model first generates a set of
> desirable intermediate latent variables, which we call “imaginations”,
> e.g., 3D pose and camera viewpoint, such that these imagination matches
> what we observe. Adversarial inversion can be trained with or without
> paired supervision of standard supervised models, as it does not require
> paired annotations. It can instead exploit a large number of unlabelled
> images. We empirically show adversarial inversion outperforms previous
> state-of-the-art supervised models on 3D human pose estimation and 3D scene
> depth estimation. Further, we show interesting results on biased image
> Joint work with Adam Harley, William Seto and Katerina Fragkiadaki.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the ai-seminar-announce