nips nips2012 nips2012-176 nips2012-176-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Tomasz Trzcinski, Mario Christoudias, Vincent Lepetit, Pascal Fua
Abstract: In this paper we apply boosting to learn complex non-linear local visual feature representations, drawing inspiration from its successful application to visual object detection. The main goal of local feature descriptors is to distinctively represent a salient image region while remaining invariant to viewpoint and illumination changes. This representation can be improved using machine learning, however, past approaches have been mostly limited to learning linear feature mappings in either the original input or a kernelized input feature space. While kernelized methods have proven somewhat effective for learning non-linear local feature descriptors, they rely heavily on the choice of an appropriate kernel function whose selection is often difficult and non-intuitive. We propose to use the boosting-trick to obtain a non-linear mapping of the input to a high-dimensional feature space. The non-linear feature mapping obtained with the boosting-trick is highly intuitive. We employ gradient-based weak learners resulting in a learned descriptor that closely resembles the well-known SIFT. As demonstrated in our experiments, the resulting descriptor can be learned directly from intensity patches achieving state-of-the-art performance. 1
[1] Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. IJCV 20(2) (2004) 91–110 8
[2] Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded Up Robust Features. In: ECCV’06
[3] Shakhnarovich, G.: Learning Task-Specific Similarity. PhD thesis, MIT (2006)
[4] Brown, M., Hua, G., Winder, S.: Discriminative Learning of Local Image Descriptors. PAMI (2011)
[5] Strecha, C., Bronstein, A., Bronstein, M., Fua, P.: LDAHash: Improved Matching with Smaller Descriptors. PAMI 34(1) (2012)
[6] Kulis, B., Jain, P., Grauman, K.: Fast Similarity Search for Learned Metrics. PAMI (2009) 2143–2157
[7] Shen, C., Kim, J., Wang, L., van den Hengel, A.: Positive Semidefinite Metric Learning with Boosting. In: NIPS. (2009)
[8] Jain, P., Kulis, B., Davis, J., Dhillon, I.: Metric and Kernel Learning using a Linear Transformation. JMLR (2012)
[9] Bi, J., Wu, D., Lu, L., Liu, M., Tao, Y., Wolf, M.: AdaBoost on Low-Rank PSD Matrices for Metric Learning. In: CVPR. (2011)
[10] Viola, P., Jones, M.: Rapid Object Detection Using a Boosted Cascade of Simple Features. In: CVPR’01
[11] Chapelle, O., Shivaswamy, P., Vadrevu, S., Weinberger, K., Zhang, Y., Tseng, B.: Boosted Multi-Task Learning. Machine Learning (2010)
[12] Ali, K., Fleuret, F., Hasler, D., Fua, P.: A Real-Time Deformable Detector. PAMI 34(2) (2012) 225–239
[13] Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: CVPR’05
[14] Weiss, Y., Torralba, A., Fergus, R.: Spectral Hashing. NIPS 21 (2009) 1753–1760
[15] Kulis, B., Darrell, T.: Learning to Hash with Binary Reconstructive Embeddings. In: NIPS’09
[16] Salakhutdinov, R., Hinton, G.: Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure. In: International Conference on Artificial Intelligence and Statistics. (2007)
[17] Salakhutdinov, R., Hinton, G.: Semantic Hashing. International Journal of Approximate Reasoning (2009)
[18] Grauman, K., Darrell, T.: The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features. In: ICCV’05
[19] Shen, C., Welsh, A., Wang, L.: PSDBoost: Matrix Generation Linear Programming for Positive Semidefinite Matrices Learning. In: NIPS. (2008)
[20] Jia, Y., Huang, C., Darrell, T.: Beyond Spatial Pyramids: Receptive Field Learning for Pooled Image Features. In: CVPR’12
[21] Simonyan, K., Vedaldi, A., Zisserman, A.: Descriptor Learning Using Convex Optimisation. In: ECCV’12
[22] Doll´ r, P., Tu, Z., Perona, P., Belongie, S.: Integral Channel Features. In: BMVC’09 a
[23] Torralba, A., Fergus, R., Weiss, Y.: Small Codes and Large Databases for Recognition. In: CVPR’08
[24] Ali, K., Fleuret, F., Hasler, D., Fua, P.: A Real-Time Deformable Detector. PAMI (2011)
[25] Freund, Y., Schapire, R.: A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. In: European Conference on Computational Learning Theory. (1995)
[26] Rosset, S., Zhu, J., Hastie, T.: Boosting as a Regularized Path to a Maximum Margin Classifier. JMLR (2004)
[27] Calonder, M., Lepetit, V., Ozuysal, M., Trzcinski, T., Strecha, C., Fua, P.: BRIEF: Computing a Local Binary Descriptor Very Fast. PAMI 34(7) (2012) 1281–1298
[28] Rublee, E., Rabaud, V., Konolidge, K., Bradski, G.: ORB: An Efficient Alternative to SIFT or SURF. In: ICCV’11
[29] Leutenegger, S., Chli, M., Siegwart, R.: BRISK: Binary Robust Invariant Scalable Keypoints. In: ICCV’11
[30] Vedaldi, A.: http://www.vlfeat.org/˜vedaldi/code/siftpp.html 9