publication . Preprint . 2015

Context Forest for efficient object detection with large mixture models

Modolo, Davide; Vezhnevets, Alexander; Ferrari, Vittorio;
Open Access English
  • Published: 02 Mar 2015
Abstract
We present Context Forest (ConF), a technique for predicting properties of the objects in an image based on its global appearance. Compared to standard nearest-neighbour techniques, ConF is more accurate, fast and memory efficient. We train ConF to predict which aspects of an object class are likely to appear in a given image (e.g. which viewpoint). This enables to speed-up multi-component object detectors, by automatically selecting the most relevant components to run on that image. This is particularly useful for detectors trained from large datasets, which typically need many components to fully absorb the data and reach their peak performance. ConF provides ...
Subjects
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from
44 references, page 1 of 3

[1] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part based models,” IEEE Trans. on PAMI, vol. 32, no. 9, 2010.

[2] T. Malisiewicz, A. Gupta, and A. A. Efros, “Ensemble of exemplar-svms for object detection and beyond,” in ICCV, 2011.

[3] B. Russell, A. Torralba, C. Liu, R. Ferugs, and W. Freeman, “Object recognition by scene alignment,” in NIPS, 2007.

[4] L. Breiman, “Random forests,” ML Journal, vol. 45, no. 1, pp. 5-32, 2001.

[5] A. Criminisi, J. Shotton, and E. Konukoglu, “Decision forests for classification, regression, density estimation, manifold learning and semi-supervised learning,” Microsoft Research Cambridge, Tech. Rep. MSRTR-2011-114 , 2011.

[6] S. Divvala, A. Efros, and M. Hebert, “How important are 'deformable parts' in the deformable parts model?,” in ECCV, 2012. [OpenAIRE]

[7] X. Zhu, C. Vondrick, D. Ramanan, and C. Fowlkes, “Do we need more training data or better models for object detection?,” in BMVC, 2012.

[8] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results.” http://www.pascalnetwork.org/challenges/VOC/voc2012/workshop/index.html.

[9] C. Liu, J. Yuen, and A. Torralba, “Nonparametric scene parsing: Label transfer via dense scene alignment,” in CVPR, 2009.

[10] A. Torralba, “Contextual priming for object detection,” IJCV, vol. 53, no. 2, pp. 153-167, 2003.

[11] A. Rabinovich, A. Vedaldi, C. Galleguillos, E. Wiewiora, and S. Belongie, “Objects in context,” in ICCV, 2007.

[12] J. Tighe and S. Lazebnik, “Superparsing: Scalable nonparametric image parsing with superpixels,” in ECCV, 2010.

[13] G. Heitz and D. Koller, “Learning spatial context: Using stuff to find things,” in ECCV, 2008.

[14] M. Choi, J. Lim, A. Torralba, and A. Willsky, “Exploiting hierarchical context on a large database of object categories,” in CVPR, 2010. [OpenAIRE]

[15] C. Desai, D. Ramanan, and C. Folkess, “Discriminative models for multi-class object layout,” in ICCV, 2009.

44 references, page 1 of 3
Related research
Abstract
We present Context Forest (ConF), a technique for predicting properties of the objects in an image based on its global appearance. Compared to standard nearest-neighbour techniques, ConF is more accurate, fast and memory efficient. We train ConF to predict which aspects of an object class are likely to appear in a given image (e.g. which viewpoint). This enables to speed-up multi-component object detectors, by automatically selecting the most relevant components to run on that image. This is particularly useful for detectors trained from large datasets, which typically need many components to fully absorb the data and reach their peak performance. ConF provides ...
Subjects
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from
44 references, page 1 of 3

[1] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part based models,” IEEE Trans. on PAMI, vol. 32, no. 9, 2010.

[2] T. Malisiewicz, A. Gupta, and A. A. Efros, “Ensemble of exemplar-svms for object detection and beyond,” in ICCV, 2011.

[3] B. Russell, A. Torralba, C. Liu, R. Ferugs, and W. Freeman, “Object recognition by scene alignment,” in NIPS, 2007.

[4] L. Breiman, “Random forests,” ML Journal, vol. 45, no. 1, pp. 5-32, 2001.

[5] A. Criminisi, J. Shotton, and E. Konukoglu, “Decision forests for classification, regression, density estimation, manifold learning and semi-supervised learning,” Microsoft Research Cambridge, Tech. Rep. MSRTR-2011-114 , 2011.

[6] S. Divvala, A. Efros, and M. Hebert, “How important are 'deformable parts' in the deformable parts model?,” in ECCV, 2012. [OpenAIRE]

[7] X. Zhu, C. Vondrick, D. Ramanan, and C. Fowlkes, “Do we need more training data or better models for object detection?,” in BMVC, 2012.

[8] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results.” http://www.pascalnetwork.org/challenges/VOC/voc2012/workshop/index.html.

[9] C. Liu, J. Yuen, and A. Torralba, “Nonparametric scene parsing: Label transfer via dense scene alignment,” in CVPR, 2009.

[10] A. Torralba, “Contextual priming for object detection,” IJCV, vol. 53, no. 2, pp. 153-167, 2003.

[11] A. Rabinovich, A. Vedaldi, C. Galleguillos, E. Wiewiora, and S. Belongie, “Objects in context,” in ICCV, 2007.

[12] J. Tighe and S. Lazebnik, “Superparsing: Scalable nonparametric image parsing with superpixels,” in ECCV, 2010.

[13] G. Heitz and D. Koller, “Learning spatial context: Using stuff to find things,” in ECCV, 2008.

[14] M. Choi, J. Lim, A. Torralba, and A. Willsky, “Exploiting hierarchical context on a large database of object categories,” in CVPR, 2010. [OpenAIRE]

[15] C. Desai, D. Ramanan, and C. Folkess, “Discriminative models for multi-class object layout,” in ICCV, 2009.

44 references, page 1 of 3
Related research
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue