Abstract

Most current approaches to recognition aim to be scale- invariant. However, the cues available for recognizing a 300 pixel tall ob ject are qualitatively different from those for recognizing a 3 pixel tall ob ject. We argue that for sensors with finite resolution, one should in- stead use scale-variant, or multiresolution representations that adapt in complexity to the size of a putative detection window. We describe a multiresolution model that acts as a deformable part-based model when scoring large instances and a rigid template with scoring small instances. We also examine the interplay of resolution and context, and demon- strate that context is most helpful for detecting low-resolution instances when local models are limited in discriminative power. We demonstrate impressive results on the Caltech Pedestrian benchmark, which contains ob ject instances at a wide range of scales. Whereas recent state-of-the- art methods demonstrate missed detection rates of 86%-37% at 1 false- positive-per-image, our multiresolution model reduces the rate to 29%.