Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models prov...
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...
We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
Partial differential equations (PDEs) have been successfully applied to many computer vision and image processing problems. However, designing PDEs requires high mathematical skill...
In this paper, we demonstrate the use of learning with non-uniform error-cost as a novel technique to design a multiclass cost-sensitive classifier. We investigate two important ...