Sparselet Models for Efficient Multiclass Object Detection
UC Berkeley
Proceedings of ECCV, 2012
@article{song2012sparselet,
title={Sparselet Models for Efficient Multiclass Object Detection},
author={Song, H.O. and Zickler, S. and Althoff, T. and Girshick, R. and Fritz, M. and Geyer, C. and Felzenszwalb, P. and Darrell, T.},
year={2012}
}
We develop intermediate representations for deformable part models, and show that such representations have favorable performance characteristics for multi-class problems where the number of classes is large. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This leads to an universal set of parts that are shared among all object classes. Reconstruction of part responses via sparse-matrix-multiply reduces computation relative to conventional filter convolutions. Our model is well suited to a parallel implementation, and we report a new GPU DPM implementation which takes advantage of sparse coding of part filters. The speed-up offered by our intermediate representation and parallel computation enable real-time DPM detection of 20 different object classes on a laptop computer.
July 6, 2012 by hgpu
