Improving Large-Scale Image Retrieval Through Robust Aggregation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 39, Issue 9, 2017, Pages 1783-1796

  Husain, Syed Sameed ^a   Bober, Miroslaw ^a  

^a UNIVERSITY OF SURREY   (United Kingdom)

Author keywords

global descriptor; image retrieval; local descriptor aggregation; Visual search

Indexed keywords

NEURAL NETWORKS; VECTORS;

BAG-OF-VISUAL-WORDS; CONVOLUTIONAL NEURAL NETWORK; DESCRIPTORS; GLOBAL DESCRIPTORS; LARGE-SCALE DATASETS; LOCAL DESCRIPTORS; VECTOR OF LOCALLY AGGREGATED DESCRIPTORS; VISUAL SEARCH;

IMAGE RETRIEVAL;

EID: 85029360160     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2016.2613873     Document Type: Article

References (34)

1. D. G. Lowe, "Distinctive image features from scale-invariant keypoints, " Int. J. Comput. Vis., vol. 60, pp. 91-110, 2004.
2. H. Bay, A. Ess, T. Tuytelaars, L. Van Gool, "Speeded-up robust features (SURF), " Comput. Vis. Image Understanding, vol. 110, pp. 346-359, 2008.
3. S. A. J. Winder, G. Hua, M. Brown, "Picking the best daisy, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 178-185.
4. A. Oliva and A. Torralba, "Modeling the shape of the scene: A holistic representation of the spatial envelope, " Int. J. Comput. Vis., vol. 42, pp. 145-175, 2001.
5. M. Douze, H. J-egou, H. Sandhawalia, L. Amsaleg, C. Schmid, "Evaluation of GIST descriptors for web-scale image search, " in Proc. ACM Int. Conf. Image Video Retrieval, 2009, Art. no. 19.
6. J. Sivic and A. Zisserman, "Video Google: Efficient visual search of videos, " in Toward Category-Level Object Recognition. Berlin, Germany: Springer, 2006.
7. F. Perronnin, Y. Liu, J. Sanchez, H. Poirier, "Large-scale image retrieval with compressed fisher vectors, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2010, pp. 3384-3391.
8. H. J-egou, F. Perronnin, M. Douze, J. S-anchez, P. P-erez, C. Schmid, "Aggregating local image descriptors into compact codes, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 9, pp. 1704-1716, Sep. 2012.
9. M. Bober, S. Husain, S. Paschalakis, K. Wnukowicz, "Improvements to TM6.0 with a robust visual descriptor proposal from University of Surrey and Visual Atoms, " presented at the MPEG Standardisation Meeting, Vienna, Austria, Jul. 2013.
10. S. Husain and M. Bober, "Robust and scalable aggregation of local features for ultra large scale retrieval, " in Proc. IEEE Int. Conf. Image Process., Oct. 2014, pp. 2799-2803.
11. M. Bober and S. Husain, "Compact and robust signature for large scale visual search, retrieval and classification, " WO Patent PCT/GB2014/052, 058, Jan. 15, 2015.
12. H. J-egou and O. Chum, "Negative evidences and co-occurrences in image retrieval: The benefit of PCA and whitening, " in Proc. Eur. Conf. Comput. Vis., Oct. 2012, pp. 774-787.
13. H. J-egou and A. Zisserman, "Triangulation embedding and democratic aggregation for image search, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2014, pp. 3310-3317.
14. A. Babenko and V. S. Lempitsky, "Aggregating deep convolutional features for image retrieval, " CoRR, 2015.
15. D. Nist-er and H. Stew-enius, "Scalable recognition with a vocabulary tree, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2006, pp. 2161-2168.
16. J. Philbin, O. Chum, M. Isard, J. Sivic, A. Zisserman, "Object retrieval with large vocabularies and fast spatial matching, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2007.
17. J. Philbin, M. Isard, J. Sivic, A. Zisserman, "Lost in quantization: Improving particular object retrieval in large scale image databases, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2008, pp. 1-8.
18. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition, " CoRR, 2014.
19. R. Arandjelovific and A. Zisserman, "All about VLAD, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2013, pp. 1578-1585.
20. J. Delhumeau, P.-H. Gosselin, H. J-egou, P. P-erez, "Revisiting the VLAD image representation, " in Proc. 21st ACM Int. Conf. Multimedia, Oct. 2013, pp 653-656.
21. E. S. Xioufis, S. Papadopoulos, Y. Kompatsiaris, G. Tsoumakas, I. P. Vlahavas, "A comprehensive study over VLAD and product quantization in large-scale image retrieval, " IEEE Trans. Multimedia, vol. 16, no. 6, pp. 1713-1728, Oct. 2014.
22. C. Eggert, S. Romberg, R. Lienhart, "Improving VLAD: Hierarchical coding and a refined local coordinate system, " in Proc. IEEE Int. Conf. Image Process., 2014, pp. 3018-3022.
23. Z. Liu, H. Li, W. Zhou, T. Rui, Q. Tian, "Uniforming residual vector distribution for distinctive image representation, " IEEE Trans. Circuits Syst.Video Technol., vol. 26, no. 6, pp. 375-384, Feb. 2015.
24. D. Picard and P.-H. Gosselin, "Improving image similarity with vectors of locally aggregated tensors, " in Proc. IEEE Int. Conf. Image Process., Sep. 2011, pp. 669-672.
25. R. Negrel, D. Picard, P.-H. Gosselin, "Web scale image retrieval using compact tensor aggregation of visual descriptors, " IEEE Trans. Multimedia, vol. 20, no. 3, pp. 24-33, Mar. 2013.
26. T.-T. Do, Q. D. Tran, N.-M. Cheung, "FAemb: A function approximation-based embedding method for image retrieval, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 3556-3564.
27. T. Ge, K. He, Q. Ke, J. Sun, "Optimized product quantization, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 36, no. 4, pp. 744-755, Apr. 2014.
28. C. C. Aggarwal, A. Hinneburg, D. A. Keim, "On the surprising behavior of distance metrics in high dimensional spaces, " in Proc. 8th Int. Conf. Database Theory, 2001, pp. 420-434.
29. A. S. Razavian, J. Sullivan, A. Maki, S. Carlsson, "Visual instance retrieval with deep convolutional networks, " CoRR, 2014.
30. H. J-egou, M. Douze, C. Schmid, "Improving bag-of-features for large scale image search, " Int. J. Comput. Vis., vol. 87, pp. 316-336, Feb. 2010.
31. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, "ImageNet: A large-scale hierarchical image database, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 248-255.
32. K. Mikolajczyk and C. Schmid, "Scale and affine invariant interest point detectors, " Int. J. Comput. Vis., vol. 60, pp. 63-86, 2004.
33. R. Arandjelovific and A. Zisserman, "Three things everyone should know to improve object retrieval, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2012, pp. 2911-2918.
34. Y. Gong, L. Wang, R. Guo, S. Lazebnik, "Multi-scale orderless pooling of deep convolutional activation features, " in Proc. 13th Eur. Conf. Comput. Vis., 2014, pp. 392-407.