Abstract
Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly found a large interest in a wide variety of computer vision applications such as mid-level feature learning, tracking and segmentation. What makes this technique so attractive is the possibility of associating to instance specific classifiers one or more semantic labels that can be transferred at test time. To guarantee its effectiveness though, a large collection of classifiers has to be used. This directly translates in a high computational footprint, which could make the evaluation step prohibitive. To overcome this issue we organize Exemplar-SVMs into a taxonomy, exploiting the joint distribution of Exemplar scores. This permits to index the classifiers at a logarithmic cost, while maintaining the label transfer capabilities of the method almost unaffected. We propose different formulations of the taxonomy in order to maximize the speed gain. In particular we propose a highly efficient Vector Quantized Rejecting Taxonomy to discard unpromising image regions during evaluation, performing computations in a quantized domain. This allow us to obtain ramarkable speed gains, with an improvement up to more than two orders of magnitude. To verify the robustness of our indexing data structure with reference to a standard Exemplar-SVM ensemble, we experiment with the Pascal VOC 2007 benchmark on the Object Detection competition and on a simple segmentation task.
Similar content being viewed by others
References
Aubry M, Maturana D, Efros AA, Russel BC, Sivic J (2014) Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of cad models. In: Proc. of CVPR
Aytar Y, Zisserman A (2012) Enhancing exemplar svms using part level transfer regularization. In: BMVC, pp 1–11
Becattini F, Seidenari L, Del Bimbo A (2016) Indexing ensembles of exemplar-svms with rejecting taxonomies. In: 2016 14th International workshop on content-based multimedia indexing (CBMI). IEEE, pp 1–6
Bengio S, Weston J, Grangier D (2010) Label embedding trees for large multi-class tasks. In: Proc. of NIPS
Bourdev L, Brandt J (2005) Robust object detection via soft cascade. In: Proc. of CVPR
Chen Y, MC, Ghosh J (2004) Integrating support vector machines in a hierarchical output space decomposition framework. In: Proc. of IGARSS
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proc. of CVPR, pp 886–893
Dean T, Ruzon M, Segal M, Shlens J, Vijayanarasimhan S, Yagnik J (2013) Fast, accurate detection of 100,000 object classes on a single machine. In: Proc. of CVPR. Washington, DC
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE Conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 248–255
Deng J, Ding N, Jia Y, Frome A, Murphy K, Bengio S, Li Y, Neven H, Adam H (2014) Large-scale object classification using label relation graphs. In: European conference on computer vision. Springer, pp 48–64
Deng J, Satheesh S, Berg AC, Fei-Fei L (2011) Fast and balanced: efficient label tree learning for large scale object recognition. In: Proc. of NIPS
Dubout C, Fleuret F (2012) Exact acceleration of linear object detectors. In: Proc. of ECCV, pp 301–311
Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338
Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The PASCAL visual object classes challenge (VOC2010) results
Fan J, Zhou N, Peng J, Gao L (2015) Hierarchical learning of tree classifiers for large-scale plant species identification. IEEE Trans Image Process 24(11):4172–4184
Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Pattern Anal Mach Intell. 32(9)
Gao T, Koller D (2011) Discriminative learning of relaxed hierarchy for large-scale visual recognition. In: Proc. of ICCV
Griffin G, Perona P (2008) Learning and using taxonomies for fast visual categorization. In: IEEE Conference on computer vision and pattern recognition, 2008. CVPR 2008. IEEE, pp 1–8
Gronat P, Obozinski G, Sivic J, Pajdla T (2013) Learning and calibrating per-location classifiers for visual place recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 907–914
Guillaumin M, Ferrari V (2012) Large-scale knowledge transfer for object localization in imagenet. In: 2012 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 3202–3209
Hariharan B, Malik J, Ramanan D (2012) Discriminative decorrelation for clustering and classification. In: Computer vision–ECCV 2012. Springer, pp 459–472
Jain A, Gupta A, Rodriguez M, Davis LS (2013) Representing videos using mid-level discriminative patches. In: Proc. of CVPR
Kobayashi T (2015) Three viewpoints toward exemplar svm. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2765–2773
Kuettel D, Guillaumin M, Ferrari V (2012) Segmentation propagation in imagenet. In: European conference on computer vision. Springer, pp 459–473
Liu B, Sadeghi F, Tappen M, Shamir O, Liu C (2013) Probabilistic label trees for efficient large scale image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 843–850
Malisiewicz T, Gupta A, Efros AA (2011) Ensemble of exemplar-svms for object detection and beyond. In: Proc. of ICCV
Marszałek M, Schmid C (2008) Constructing category hierarchies for visual recognition. In: Proc. of ECCV. Springer
Miller GA (1995) Wordnet: a lexical database for english. Commun ACM 38(11):39–41
Modolo D, Vezhnevets A, Ferrari V (2015) Context forest for object class detection. Arxiv preprint
Modolo D, Vezhnevets A, Russakovsky O, Ferrari V (2015) Joint calibration of ensemble of exemplar svms. In: 2015 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 3955–3963
Mrowca D, Rohrbach M, Hoffman J, Hu R, Saenko K, Darrell T (2015) Spatial semantic regularisation for large scale object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2003–2011
Ng AY, Jordan MI, Weiss Y (2002) On spectral clustering: analysis and an algorithm. In: Proc. of NIPS
Ristin M, Guillaumin M, Gall J, Gool L (2014) Incremental learning of ncm forests for large-scale image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3654–3661
Rohrbach M, Ebert S, Schiele B (2013) Transfer learning in a transductive setting. In: Advances in neural information processing systems, pp 46–54
Sadeghi MA, Forsyth D (2013) Fast template evaluation with vector quantization. In: Proc. of NIPS, pp 2949–2957
Sadeghi M, Forsyth D (2014) 30hz object detection with dpm v5. In: Proc. of ECCV, lecture notes in computer science, vol 8689. Springer International Publishing, pp 65–79
Singh S, Gupta A, Efros AA (2012) Unsupervised discovery of mid-level discriminative patches. In: Proc. of ECCV
Spielmat DA, Teng SH (1996) Spectral partitioning works: planar graphs and finite element meshes. In: 37th Annual symposium on foundations of computer science, 1996. Proceedings. IEEE, pp 96–105
Tighe J, Lazebnik S (2013) Finding things: image parsing with regions and per-exemplar detectors. In: Proc. of CVPR
Viola P, Jones MJ (2004) Robust real-time face detection. Int J Comput Vis 57(2):137–154
Von Luxburg U (2007) A tutorial on spectral clustering. Stat Comput 17(4):395–416
Vondrick C, Khosla A, Malisiewicz T, Torralba A (2013) Hoggles: visualizing object detection features. In: Proc. of ICCV
Yao B, Khosla A, Fei-Fei L (2011) Combining randomization and discrimination for fine-grained image categorization. In: 2011 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 1577–1584
Zepeda J, Perez P (2015) Exemplar svms as visual feature encoders. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3052–3060
Acknowledgements
Federico Becattini and Lorenzo Seidenari are partially supported by “THE SOCIAL MUSEUM AND SMART TOURISM”, MIUR project no. CTN01_00034_23154_SMST.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Becattini, F., Seidenari, L. & Del Bimbo, A. Indexing quantized ensembles of exemplar-SVMs with rejecting taxonomies. Multimed Tools Appl 76, 22647–22668 (2017). https://doi.org/10.1007/s11042-017-4794-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-4794-7