Browse > Article
http://dx.doi.org/10.5626/JCSE.2017.11.1.1

Memory-Efficient NBNN Image Classification  

Lee, YoonSeok (School of Computing, Korea Advanced Institute of Science and Technology (KAIST))
Yoon, Sung-Eui (School of Computing, Korea Advanced Institute of Science and Technology (KAIST))
Publication Information
Journal of Computing Science and Engineering / v.11, no.1, 2017 , pp. 1-8 More about this Journal
Abstract
Naive Bayes nearest neighbor (NBNN) is a simple image classifier based on identifying nearest neighbors. NBNN uses original image descriptors (e.g., SIFTs) without vector quantization for preserving the discriminative power of descriptors and has a powerful generalization characteristic. However, it has a distinct disadvantage. Its memory requirement can be prohibitively high while processing a large amount of data. To deal with this problem, we apply a spherical hashing binary code embedding technique, to compactly encode data without significantly losing classification accuracy. We also propose using an inverted index to identify nearest neighbors among binarized image descriptors. To demonstrate the benefits of our method, we apply our method to two existing NBNN techniques with an image dataset. By using 64 bit length, we are able to reduce memory 16 times with higher runtime performance and no significant loss of classification accuracy. This result is achieved by our compact encoding scheme for image descriptors without losing much information from original image descriptors.
Keywords
Image classification; NBNN; Hashing; Memory efficiency; Indexing;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 I. Kuzborskij, F. Maria Carlucci, and B. Caputo, "When naive Bayes nearest neighbors meet convolutional neural networks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 2100-2109.
2 A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in Neural Information Processing Systems, vol. 25, pp. 1097-1105, 2012.
3 R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, 2014, pp. 580-587.
4 N. Zhang, J. Donahue, R. Girshick, and T. Darrell, "Partbased R-CNNs for fine-grained category detection," in Proceedings of European Conference on Computer Vision, Zurich, Switzerland, 2014, pp. 834-849.
5 L. Xie, R. Hong, B. Zhang, and Q. Tian, "Image classification and retrieval are one," in Proceedings of the 5th ACM on International Conference on Multimedia Retrieval (ICMR), Shanghai, China, 2015, pp. 3-10.
6 T. Tuytelaars, M. Fritz, K. Saenko, and T. Darrell, "The NBNN kernel," in Proceedings of 2011 IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011, pp. 1824-1831.
7 S. McCann and D. G. Lowe, "Local naive Bayes nearest neighbor for image classification," in Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, 2012, pp. 3650-3656.
8 M. Sun, Y. Lee, and S. E. Yoon, "Relation based Bayesian network for NBNN," Journal of Computing Science and Engineering, vol. 9, no. 4, pp. 204-213, 2015.   DOI
9 T. Tommasi and B. Caputo, "Frustratingly easy NBNN domain adaptation," in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, 2013, pp. 897-904.
10 R. Behmo, P. Marcombes, A. Dalalyan, and V. Prinet, "Towards optimal naive Bayes nearest neighbor," in Proceedings of European Conference on Computer Vision, Crete, Greece, 2010, pp. 171-184.
11 J. H. Friedman, J. L. Bentley, and R. A. Finkel, "An algorithm for finding best matches in logarithmic expected time," ACM Transactions on Mathematical Software (TOMS), vol. 3, no. 3, pp. 209-226, 1977.   DOI
12 K. Kim, M. K. Hasan, J. P. Heo, Y. W. Tai, and S. E. Yoon, "Probabilistic cost model for nearest neighbor search in image retrieval," Computer Vision and Image Understanding, vol. 116, no. 9, pp. 991-998, 2012.   DOI
13 C. Silpa-Anan and R. Hartley, "Optimised KD-trees for fast image descriptor matching," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AK, 2008, pp. 1-8.
14 Y. Jia, J. Wang, G. Zeng, H. Zha, and X. S. Hua, "Optimizing kd-trees for scalable visual descriptor indexing," in Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, 2010, pp. 3392-3399.
15 M. Muja and D. G. Lowe, "Fast approximate nearest neighbors with automatic algorithm configuration," in Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), Lisbon, Portugal, 2009, pp. 331-340.
16 J. Wang, S. Kumar, and S. F. Chang, "Semi-supervised hashing for scalable image retrieval," in Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, 2010, pp. 3424-3431.
17 J. Pan and D. Manocha, "Fast GPU-based locality sensitive hashing for k-nearest neighbor computation," in Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Chicago, IL, 2011, pp. 211-220.
18 Y. Gong and S. Lazebnik, "Iterative quantization: a procrustean approach to learning binary codes," in Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, 2011, pp. 817-824.
19 P. Indyk and R. Motwani, "Approximate nearest neighbors: towards removing the curse of dimensionality," in Proceedings of the 30th Annual ACM Symposium on Theory of Computing, Dallas, TX, 1998, pp. 604-613.
20 M. Datar, N. Immorlica, P. Indyk, and V. S. Mirrokni, "Locality-sensitive hashing scheme based on p-stable distributions," in Proceedings of the 20th Annual Symposium on Computational Geometry, Brooklyn, NY, 2004, pp. 253-262.
21 J. P. Heo, Y. Lee, J. He, S. F. Chang, and S. E. Yoon, "Spherical hashing," in Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, 2012, pp. 2957-2964.
22 H. Jegou, M. Douze, and C. Schmid, "Product quantization for nearest neighbor search," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 1, pp. 117-128, 2011.   DOI
23 J. P. Heo, Z. Lin, X. Shen, J. Brandt, and S. E. Yoon, "Shortlist selection with residual-aware distance estimator for k-nearest neighbor search," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 2009-2017.
24 L. Fei-Fei, R. Fergus, and P. Perona, "Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Washington, DC, 2004, pp. 1-9.
25 O. Boiman, E. Schechtman, and M. Irani, "In defense of nearest neighbor based image classification," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AK, 2008, pp. 1-8.
26 D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.   DOI
27 S. E. Yoon, C. Lauterbach, and D. Manocha, "R-LODs: fast LOD-based ray tracing of massive models," The Visual Computer, vol. 22, no. 9, pp. 772-784, 2006.   DOI
28 O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, et al., "ImageNet large scale visual recognition challenge," International Journal of Computer Vision, vol. 115, no. 3, pp. 211-252, 2015.   DOI