Learning Robust Representations for Computer Vision
This work addresses robustness in computer vision representation learning, offering incremental improvements for tasks like background separation and facial image clustering.
The paper tackled the problem of noise and outliers in unsupervised representation learning for computer vision by developing robust PCA and spectral clustering methods, achieving superior performance on real-world test sets.
Unsupervised learning techniques in computer vision often 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.