我們提出一個有效的圖像表示法，稱之為“隨機分解樹群”(RDFS)。此方法是基於樹狀結構的編碼並結合視覺字為基礎的表示法。一個“隨機分解樹群”(RDF)能夠利用遞迴以及隨機的方式將圖像的局部特徵向量分解成由不同組合的視覺字來描述。當我們利用標準多尺度的局部特徵向量和空間匯集的策略時，由“隨機分解樹群”產生的代碼在圖像分類的表現上有不錯的效果。同時，我們的數據結果在幾個標準數據庫上與其他有名的方法並駕齊驅。

We present an effective image representation based on a new tree-structured coding technique called `random decomposition forests' (RDFs). Our method combines the merits of visual-word based representations and random forests. An RDF is able to decompose a local descriptor into multiple sets of visual words in a recursive and randomized manner. We show that, when combined with standard multiscale and spatial pooling strategies, the code vectors generated by the RDF yield a powerful representation for image categorization, and can achieve state-of-the-art performance on several popular benchmark datasets.

[1] Liefeng Bo and Cristian Sminchisescu. Ecient match kernel between sets of features for visual recognition. In NIPS, pages 135-143, 2009.
[2] Oren Boiman, Eli Shechtman, and Michal Irani. In defense of nearest-neighbor based image classication. In CVPR, 2008.
[3] Navneet Dalal and Bill Triggs. Histograms of oriented gradients for human detection. In CVPR(1), pages 886-893, 2005.
[4] Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. LIBLINEAR: A library for large linear classication. Journal of Machine Learning Research, 9:1871-1874, 2008.
[5] Li Fei-Fei, Rob Fergus, and Pietro Perona. Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12, CVPRW'04, pages 178-, Washington, DC, USA, 2004. IEEE Computer Society.
[6] G. Grin, A. Holub, and P. Perona. Caltech-256 object category dataset. Technical Report 7694, California Institute of Technology, 2007.
[7] Svetlana Lazebnik, Cordelia Schmid, and Jean Ponce. Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories. In CVPR(2), pages 2169-2178, 2006.
[8] Fei-Fei Li and Pietro Perona. A bayesian hierarchical model for learning natural scene categories. In CVPR(2), pages 524-531, 2005.
[9] David G. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2):91-110, 2004.
[10] Julien Mairal, Francis Bach, Jean Ponce, and Guillermo Sapiro. Online dictionary learning for sparse coding. In ICML, page 87, 2009.
[11] Sancho McCann and David G. Lowe. Local naive bayes nearest neighbor for image classication. In CVPR, pages 3650-3656, 2012.
[12] Florent Perronnin and Christopher R. Dance. Fisher kernels on visual vocabularies for image categorization. In CVPR, 2007.
[13] Florent Perronnin, Jorge Sanchez, and Thomas Mensink. Improving the fisher kernel for large-scale image classification. In ECCV(4), pages 143-156, 2010.
[14] Tinne Tuytelaars, Mario Fritz, Kate Saenko, and Trevor Darrell. The nbnn kernel. In ICCV, pages 1824-1831, 2011.
[15] Jinjun Wang, Jianchao Yang, Kai Yu, Fengjun Lv, Thomas S. Huang, and Yihong Gong. Locality-constrained linear coding for image classication. In CVPR,pages 3360-3367, 2010.
[16] Jianchao Yang, Kai Yu, Yihong Gong, and Thomas S. Huang. Linear spatial pyramid matching using sparse coding for image classication. In CVPR, pages 1794-1801, 2009.
[17] Hao Zhang, Alexander C. Berg, Michael Maire, and Jitendra Malik. Svm-knn:Discriminative nearest neighbor classication for visual category recognition. In CVPR(2), pages 2126-2136, 2006.