Abstract
We propose a method for accelerating computation of an object detector based on a linear classifier when objects are expressed by binary feature vectors. Our key idea is to decompose a real-valued weight vector of the linear classifier into a weighted sum of a few ternary basis vectors so as to preserve the original classification scores. Our data-dependent decomposition algorithm can approximate the original classification scores by a small number of the ternary basis vectors with an allowable error. Instead of using the original real-valued weight vector, the approximated classification score can be obtained by evaluating the few inner products between the binary feature vector and the ternary basis vectors, which can be computed using extremely fast logical operations. We also show that each evaluation of the inner products can be cascaded for incorporating early termination. Our experiments revealed that the linear filtering used in a HOG-based object detector becomes 36.9× faster than the original implementation with 1.5% loss of accuracy for 0.1 false positives per image in pedestrian detection task.
Chapter PDF
Similar content being viewed by others
References
Ambai, M., Yoshida, Y.: CARD: Compact and real-time descriptors. In: ICCV, pp. 97–104 (2011)
Cheng, M.-M., Zhang, Z., Lin, W.-Y., Torr, P.: BING: Binarized normed gradients for objectness estimation at 300fps. In: CVPR (2014)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: An evaluation of the state of the art. In: PAMI, pp. 743–761 (2012)
Dubout, C., Fleuret, F.: Exact acceleration of linear object detectors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 301–311. Springer, Heidelberg (2012)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Cascade object detection with deformable part models. In: CVPR, pp. 2241–2248 (2010)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. In: PAMI, pp. 1627–1645 (2010)
Gong, S.Y., Lazebnik: Iterative quantization: A procrustean approach to learning binary codes. In: CVPR, pp. 817–824 (2011)
Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features. In: ICCV, pp. 1458–1465 (2005)
Hare, S., Saffari, A., Torr, P.H.S.: Efficient online structured output learning for keypoint-based object tracking. In: CVPR, pp. 1894–1901 (2012)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)
Lampert, C.H., Blaschko, M.B., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: CVPR, pp. 1–8 (2008)
Leutenegger, S., Chli, M., Siegwart, R.Y.: BRISK: Binary robust invariant scalable keypoints. In: ICCV, pp. 2548–2555 (2011)
Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: CVPR, pp. 1–8 (2008)
F., Perronnin, Y.L., Sanchez, J., Poirier, H.: Large-scale image retrieval with compressed fisher vectors. In: CVPR, pp. 3384–3391 (2010)
Perronnin, F., Sánchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143–156. Springer, Heidelberg (2010)
Rigamonti, R., Sironi, A., Lepetit, V., Fua, P.: Learning separable filters. In: CVPR, pp. 2754–2761 (2013)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: An efficient alternative to SIFT or SURF. In: ICCV, pp. 2564–2571 (2011)
Song, H.O., Girshick, R., Darrell, T.: Discriminatively activated sparselets. In: ECCV, pp. 196–204 (2013)
Song, H.O., Zickler, S., Althoff, T., Girshick, R., Fritz, M., Geyer, C., Felzenszwalb, P., Darrell, T.: Sparselet models for efficient multiclass object detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 802–815. Springer, Heidelberg (2012)
Vedaldi, A., Zisserman, A.: Efficient additive kernels via explicit feature maps. In: PAMI, pp. 480–492 (2012)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR, pp. 511–518 (2001)
Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: NIPS, pp. 1753–1760 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Ambai, M., Sato, I. (2014). SPADE: Scalar Product Accelerator by Integer Decomposition for Object Detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8693. Springer, Cham. https://doi.org/10.1007/978-3-319-10602-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-10602-1_18
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10601-4
Online ISBN: 978-3-319-10602-1
eBook Packages: Computer ScienceComputer Science (R0)