Abstract

this article, we describe our work to test a simple analytical model that captures several trade-offs governing the performance of visual recognition systems based on spatially invariant conjunctive features. In addition, we introduce a supervised greedy algorithm for feature learning that grows a visual representation in such a way as to minimize false-positive recognition errors. Finally, we consider some of the surprising properties of "good" representations and the implications of our results for more realistic visual recognition problems.

Citations