Shufflets: Shared Mid-level Parts for Fast Object Detection

We present a method to identify and exploit structures that are shared across different object categories, by using sparse coding to learn a shared basis for the ´part´ and ´root´ templates of Deformable Part Models (DPMs).Our first contribution consists in using Shift-Invariant Sparse Coding (SISC) to learn mid-level elements that can translate during coding. This results in systematically better approximations than those attained using standard sparse coding. To emphasize that the learned mid-level structures are shiftable we call them shufflets.Our second contribution consists in using the resulting score to construct probabilistic upper bounds to the exact template scores, instead of taking them ´at face value´ as is common in current works. We integrate shufflets in Dual- Tree Branch-and-Bound and cascade-DPMs and demonstrate that we can achieve a substantial acceleration, with practically no loss in performance.