Timezone: »

Fast Training of Pose Detectors in the Fourier Domain
João Henriques · Pedro Martins · Rui F Caseiro · Jorge Batista

Tue Dec 09 04:00 PM -- 08:59 PM (PST) @ Level 2, room 210D

In many datasets, the samples are related by a known image transformation, such as rotation, or a repeatable non-rigid deformation. This applies to both datasets with the same objects under different viewpoints, and datasets augmented with virtual samples. Such datasets possess a high degree of redundancy, because geometrically-induced transformations should preserve intrinsic properties of the objects. Likewise, ensembles of classifiers used for pose estimation should also share many characteristics, since they are related by a geometric transformation. By assuming that this transformation is norm-preserving and cyclic, we propose a closed-form solution in the Fourier domain that can eliminate most redundancies. It can leverage off-the-shelf solvers with no modification (e.g. libsvm), and train several pose classifiers simultaneously at no extra cost. Our experiments show that training a sliding-window object detector and pose estimator can be sped up by orders of magnitude, for transformations as diverse as planar rotation, the walking motion of pedestrians, and out-of-plane rotations of cars.

Author Information

João Henriques (University of Oxford)
Pedro Martins (University of Coimbra)
Rui F Caseiro (University of Coimbra)
Jorge Batista (University of Coimbra)

More from the Same Authors