Sparselet Models for Efficient Multiclass Object Detection

Abstract

We develop an intermediate representation for deformable part models and show that this representation has favorable performance characteristics for multi-class problems when the number of classes is high. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This leads to a universal set of parts that are shared among all object classes. Reconstruction of the original part filter responses via sparse matrix-vector product reduces computation relative to conventional part filter convolutions. Our model is well suited to a parallel implementation, and we report a new GPU DPM implementation that 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.

Cite

Text

Song et al. "Sparselet Models for Efficient Multiclass Object Detection." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33709-3_57

Markdown

[Song et al. "Sparselet Models for Efficient Multiclass Object Detection." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/song2012eccv-sparselet/) doi:10.1007/978-3-642-33709-3_57

BibTeX

@inproceedings{song2012eccv-sparselet,
  title     = {{Sparselet Models for Efficient Multiclass Object Detection}},
  author    = {Song, Hyun Oh and Zickler, Stefan and Althoff, Tim and Girshick, Ross B. and Fritz, Mario and Geyer, Christopher and Felzenszwalb, Pedro F. and Darrell, Trevor},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {802-815},
  doi       = {10.1007/978-3-642-33709-3_57},
  url       = {https://mlanthology.org/eccv/2012/song2012eccv-sparselet/}
}