Abstract
Image representations derived from simplified models of the primary visual cortex (V1), such as HOG and SIFT, elicit good perfor- mance in a myriad of visual classification tasks including ob ject recogni- tion/detection, pedestrian detection and facial expression classification. A central question in the vision, learning and neuroscience communi- ties regards why these architectures perform so well. In this paper, we offer a unique perspective to this question by subsuming the role of V1- inspired features directly within a linear support vector machine (SVM). We demonstrate that a specific class of such features in conjunction with a linear SVM can be reinterpreted as inducing a weighted margin on the Kronecker basis expansion of an image. This new viewpoint on the role of V1-inspired features allows us to answer fundamental questions on the uniqueness and redundancies of these features, and offer substantial improvements in terms of computational and storage efficiency.