cvpr cvpr2013 cvpr2013-212 cvpr2013-212-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Zhile Ren, Gregory Shakhnarovich
Abstract: We propose a hierarchical segmentation algorithm that starts with a very fine oversegmentation and gradually merges regions using a cascade of boundary classifiers. This approach allows the weights of region and boundary features to adapt to the segmentation scale at which they are applied. The stages of the cascade are trained sequentially, with asymetric loss to maximize boundary recall. On six segmentation data sets, our algorithm achieves best performance under most region-quality measures, and does it with fewer segments than the prior work. Our algorithm is also highly competitive in a dense oversegmentation (superpixel) regime under boundary-based measures.
[1] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. S ¨usstrunk. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE TPAMI, 2012.
[2] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik. Contour detection and hierarchical image segmentation. IEEE TPAMI, 33(5), 2011.
[3] J. Carreira, R. Caseiro, J. Batista, and C. Sminchisescu. Semantic segmentation with second-order pooling. In ECCV, 2012.
[4] D. Comaniciu and P. Meer. Mean shift: A robust approach toward feature space analysis. IEEE TPAMI, 24(5), 2002.
[5] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2012 (VOC2012). http://www.pascalnetwork.org/challenges/VOC/voc2012.
[6] P. Felzenszwalb and D. Huttenlocher. Efficient graph-based image segmentation. IJCV, 59(2), 2004.
[7] B. Fulkerson, A. Vedaldi, and S. Soatto. Class segmentation and object localization with superpixel neighborhoods. In ICCV, 2009.
[8] M. Galun, E. Sharon, R. Basri, and A. Brandt. Texture segmentation by multiscale aggregation of filter responses and shape elements. In ICCV, 2003.
[9] S. Gould, R. Fulton, and D. Koller. Decomposing a scene into geometric and semantically consistent regions. In ICCV, 2009.
[10] D. Hoiem, A. Efros, and M. Hebert. Geometric context from a single image. In ICCV. IEEE, 2005.
[11] D. Hoiem, A. Efros, and M. Hebert. Recovering occlusion boundaries from an image. IJCV, 91(3), 2011.
[12] S. Kim, S. Nowozin, P. Kohli, and C. D. Yoo. Higher-order correlation clustering for image segmentation. In NIPS, 2011.
[13] A. Levinshtein, A. Stere, K. Kutulakos, D. Fleet, S. Dick- inson, and K. Siddiqi. Turbopixels: Fast superpixels using geometric flows. IEEE TPAMI, 3 1(12), 2009.
[14] M.-Y. Liu, O. Tuzel, S. Ramalingam, and R. Chellappa. Entropy rate superpixel segmentation. In CVPR, 2011. 222000111755 eastcengsryem#1320 0 .9B5SD0.390 .850B95SD 05.9 0.85 9M5SR0C.9 8A5S le0.v9Ve5OlC02.91 0.85 9 0.SB0D.8509N.8Y5UIEgHSRPoLCiIbSeC−RmoAwet−aulc,2m01 enrsPoic0 .182460EgHSILPRCoibeS−mAowetB−aulS,c2mD0R1eS.c53al01FiguserPcnoi0 .5864210.BoIHSEguLRPCnSbiIe−mdBAowaSetr−DuyRl,ce0S2mp.5a1rl0ecison-r1alcuvenoisrP0 .642To0p.rIEgHSRPoLiCSIbge−Rm0hoAw.te4S−cauRoBl,2emr0cDn1a.l6eris08dal.1 Proicens0 .68240ISHEgoLRPC0iIbSRe−.m4AowetN−aulRcY,m0e2U.61al08 Figure 4. Average number of segments BSDS300 to achieve desired ASA. BSDS500 tergnSaoitmdnUe0 .256401 VOC#S2e0IHgESLPomR1CIibeS2R−mAnowtes−aulc,m201 oitnemgSrdnUa0 .642051 S#BeDgIEHSmRPoLCSiIbe −RnmoAtswe−aulc,m201 UStongamerdnti0. 12.35 01 #SegIHmEgSLRPCeoSIbiCRne−tmAsowet−aulc,m201 taemgSrdnUei o0 .642501 #SegIEHSmRPoLCSiIbeC−RnmoAtswe−aulc,m201 mtndegUiSratoen0 .453210 M#SRegIHESCmoLRPIeSbiCn−mAtoswe−aulc,m201 NYU SnoiearUnmtdge01.5SEgIHPLoRCbiIeS−mAowet−aulc,m201 50 100 #Segments Figure 6. Under-segmentation in superpixel regime. Lower values are 1000 better.
[15] T. Malisiewicz and A. A. Efros. Improving spatial support for objects via multiple segmentations. In BMVC, September 2007.
[16] D. Martin, C. Fowlkes, D. Tal, and J. Malik. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In ICCV, volume 2, July 2001 .
[17] X. Ren and J. Malik. Learning a classification model for segmentation. In ICCV. IEEE, 2003.
[18] J. Shi and J. Malik. Normalized cuts and image segmentation. IEEE TPAMI, 22(8), 2000.
[19] J. Shotton, J. Winn, C. Rother, and A. Criminisi. TextonBoost: Joint Appearance, Shape and Context Modeling
[20]
[21]
[22]
[23]
[24]
[25] for Multi-Class Object Recognition and Segmentation. In ECCV, 2006. N. Silberman, D. Hoiem, P. Kohli, and R. Fergus. Indoor segmentation and support inference from rgbd images. In ECCV, 2012. M. Van den Bergh, X. Boix, G. Roig, B. de Capitani, and L. Van Gool. SEEDS: Superpixels Extracted via EnergyDriven Sampling. In ECCV, 2012. O. Veksler, Y. Boykov, and P. Mehrani. Superpixels and supervoxels in an energy optimization framework. ECCV, 2010. P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In CVPR, 2001 . D. Weiss and B. Taskar. SCALPEL: Segmentation CAscades with Localized Priors and Efficient Learning. In CVPR, 2013. K. Yamaguchi, T. Hazan, D. McAllester, and R. Urtasun. Continuous markov random fields for robust stereo estimation. In ECCV, 2012. 222000111 686