Infinite Feature Selection

Giorgio Roffo, Simone Melzi, Marco Cristani; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 4202-4210

Filter-based feature selection has become crucial in many classification settings, especially object recognition, recently faced with feature learning strategies that originate thousands of cues. In this paper, we propose a feature selection method exploiting the convergence properties of power series of matrices, and introducing the concept of infinite feature selection (Inf-FS). Considering a selection of features as a path among feature distributions and letting these paths tend to an infinite number permits the investigation of the importance (relevance and redundancy) of a feature when injected into an arbitrary set of cues. Ranking the importance individuates candidate features, which turn out to be effective from a classification point of view, as proved by a thoroughly experimental section. The Inf-FS has been tested on thirteen diverse benchmarks, comparing against filters, embedded methods, and wrappers; in all the cases we achieve top performances, notably on the classification tasks of PASCAL VOC 2007-2012.