Fast Template Evaluation with Vector Quantization

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 [1] by an order of magnitude and Deformable Part models [2] by two orders of magnitude with no loss of accuracy.

[1]  Axthonv G. Oettinger,et al.  IEEE Transactions on Information Theory , 1998 .

[2]  Piotr Indyk,et al.  Approximate nearest neighbors: towards removing the curse of dimensionality , 1998, STOC '98.

[3]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  David L. Neuhoff,et al.  Quantization , 2022, IEEE Trans. Inf. Theory.

[5]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2007, ICML '07.

[8]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  David A. McAllester,et al.  Cascade object detection with deformable part models , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Cordelia Schmid,et al.  Product Quantization for Nearest Neighbor Search , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Alexei A. Efros,et al.  Ensemble of exemplar-SVMs for object detection and beyond , 2011, 2011 International Conference on Computer Vision.

[12]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..

[13]  Iasonas Kokkinos.  Bounding Part Scores for Rapid Detection with Deformable Part Models , 2012, ECCV Workshops.

[14]  Andrew Zisserman,et al.  Sparse kernel approximations for efficient classification and detection , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Alexei A. Efros,et al.  Unsupervised Discovery of Mid-Level Discriminative Patches , 2012, ECCV.

[16]  Antonio Torralba,et al.  Inverting and Visualizing Features for Object Detection , 2012, ArXiv.

[17]  François Fleuret,et al.  Exact Acceleration of Linear Object Detectors , 2012, ECCV.

[18]  Alexei A. Efros,et al.  How Important Are "Deformable Parts" in the Deformable Parts Model? , 2012, ECCV Workshops.

[19]  Deva Ramanan,et al.  Histograms of Sparse Codes for Object Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Pascal Fua,et al.  Fast Object Detection with Entropy-Driven Evaluation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Jonathon Shlens,et al.  Fast, Accurate Detection of 100,000 Object Classes on a Single Machine , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Derek Hoiem,et al.  Learning Collections of Part Models for Object Recognition , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Subhransu Maji,et al.  Efficient Classification for Additive Kernel SVMs , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Hyung Jeong Yang,et al.  Recursive Coarse-to-Fine Localization for Fast Object Detection , 2014 .