Sciweavers

Share
CVPR
2012
IEEE

Robust Boltzmann Machines for recognition and denoising

9 years 2 months ago
Robust Boltzmann Machines for recognition and denoising
While Boltzmann Machines have been successful at unsupervised learning and density modeling of images and speech data, they can be very sensitive to noise in the data. In this paper, we introduce a novel model, the Robust Boltzmann Machine (RoBM), which allows Boltzmann Machines to be robust to corruptions. In the domain of visual recognition, the RoBM is able to accurately deal with occlusions and noise by using multiplicative gating to induce a scale mixture of Gaussians over pixels. Image denoising and inpainting correspond to posterior inference in the RoBM. Our model is trained in an unsupervised fashion with unlabeled noisy data and can learn the spatial structure of the occluders. Compared to standard algorithms, the RoBM is significantly better at recognition and denoising on several face databases.
Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hi
Added 28 Sep 2012
Updated 28 Sep 2012
Type Journal
Year 2012
Where CVPR
Authors Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton
Comments (0)
books