Abstract

Independent representations have recently attracted signifi- cant attention from the biological vision and cognitive science commu- nities. It has been 1) argued that properties such as sparseness and in- dependence play a ma jor role in visual perception, and 2) shown that imposing such properties on visual representations originates receptive fields similar to those found in human vision. We present a study of the impact of feature independence in the performance of visual recognition architectures. The contributions of this study are of both theoretical and empirical natures, and support two main conclusions. The first is that the intrinsic complexity of the recognition problem (Bayes error) is higher for independent representations. The increase can be significant, close to 10% in the databases we considered. The second is that criteria commonly used in independent component analysis are not su?cient to eliminate all the dependencies that impact recognition. In fact, “indepen- dent components” can be less independent than previous representations, such as principal components or wavelet bases.