Publication
ICCVW 2017
Conference paper

Learning Robust Representations for Computer Vision

View publication

Abstract

Unsupervised learning techniques in computer vision of ten require learning latent representations, such as low-dimensional linear and non-linear subspaces. Noise and outliers in the data can frustrate these approaches by obscuring the latent spaces. Our main goal is deeper understanding and new development of robust approaches for representation learning. We provide a new interpretation for existing robust approaches and present two specific contributions: a new robust PCA approach, which can separate foreground features from dynamic background, and a novel robust spectral clustering method, that can cluster facial images with high accuracy. Both contributions show superior performance to standard methods on real-world test sets.

Date

01 Jul 2017

Publication

ICCVW 2017

Authors

Share