Applying linear templates is an integral part of many object detection systems and accounts for a significant portion of computation time. We describe a method that achieves a substantial end-to-end speedup over the best current methods, without loss of accuracy. Our method is a combination of approximating scores by vector quantizing feature windows and a number of speedup techniques including cascade. Our procedure allows speed and accuracy to be traded off in two ways: by choosing the number of Vector Quantization levels, and by choosing to rescore windows or not. Our method can be directly plugged into any recognition system that relies on linear templates. We demonstrate our method to speed up the original Exemplar SVM detector  by an order of magnitude and Deformable Part models  by two orders of magnitude with no loss of accuracy.
Mohammad Amin Sadeghi (University of Illinois at Urbana-Champaign)
David Forsyth (University of Illinois at Urbana-Champaign)
More from the Same Authors
2016 Poster: Swapout: Learning an ensemble of deep architectures »
Saurabh Singh · Derek Hoiem · David Forsyth