Robust Boltzmann Machines for recognition and denoising
Citations Over TimeTop 10% of 2012 papers
Abstract
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 in-painting 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.
Related Papers
- → An Overview of Restricted Boltzmann Machines(2019)41 cited
- → Outperforming RBM Feature-Extraction Capabilities by “Dreaming” Mechanism(2022)25 cited
- → Approximate Learning Algorithm for Restricted Boltzmann Machines(2008)7 cited
- → Deep Restricted Boltzmann Networks(2016)11 cited
- → On the equivalence of Hopfield Networks and Boltzmann Machines(2011)1 cited