Abstract

We develop an intermediate representation for deformable part models and show that this representation has favorable performance characteristics for multi-class problems when the number of classes is high. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This leads to a universal set of parts that are shared among all ob ject classes. Re- construction of the original part filter responses via sparse matrix-vector product reduces computation relative to conventional part filter convo- lutions. Our model is well suited to a parallel implementation, and we report a new GPU DPM implementation that takes advantage of sparse coding of part filters. The speed-up offered by our intermediate repre- sentation and parallel computation enable real-time DPM detection of 20 different ob ject classes on a laptop computer.