In the companion paper published in CVPR 2013, we presented a method that can
directly use deformable part models (DPMs) trained as in [Felzenszwalb et al CVPR
2008]. After training, HOG based part filters are hashed, and, during inference,
counts of hashing collisions summed over all hash bands serve as a proxy for
part-filter / sliding-window dot products, i.e., filter responses. These counts are
an approximation and so we take the original HOG-based filters for the top hash
counts and calculate the exact dot products for scoring.
It is possible to train DPM models not on HOG data but on a hashed WTA [Yagnik et
al ICCV 2011] version of this data. The resulting part filters are sparse,
real-valued vectors the size of WTA vectors computed from sliding windows. Given
the WTA hash of a window, we exactly recover dot products of the top responses
using an extension of locality-sensitive hashing. In this supplement, we sketch a
method for training such WTA-based models.