Tensor-based approach to accelerate deformable part models
This work addresses computational efficiency for computer vision systems relying on convolutions, but it is incremental as it builds on existing DPM methods.
The paper tackles the speed bottleneck in systems using convolutions, specifically applying a tensor-based method to deformable part models (DPM) to reduce computational cost while maintaining accuracy. Experiments on databases like Pascal VOC show a reduction in convolutions by up to 4.5 times compared to DPM v.5 with similar accuracy.
This article provides next step towards solving speed bottleneck of any system that intensively uses convolutions operations (e.g. CNN). Method described in the article is applied on deformable part models (DPM) algorithm. Method described here is based on multidimensional tensors and provides efficient tradeoff between DPM performance and accuracy. Experiments on various databases, including Pascal VOC, show that the proposed method allows decreasing a number of convolutions up to 4.5 times compared with DPM v.5, while maintaining similar accuracy. If insignificant accuracy degradation is allowable, higher computational gain can be achieved. The method consists of filters tensor decomposition and convolutions shortening using the decomposed filter. Mathematical overview of the proposed method as well as simulation results are provided.