Local Label Descriptor for Example Based Semantic Image Labeling

详细信息    查看全文

• 作者：Yiqing Yang (21)
  Zhouyuan Li (21)
  Li Zhang (21)
  Christopher Murphy (22)
  Jim Ver Hoeve (21)
  Hongrui Jiang (21)
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2012
• 出版时间：2012
• 年：2012
• 卷：7578
• 期：1
• 页码：376-389
• 全文大小：796KB
• 参考文献：1. Kontschieder, P., Bulo, S., Bischof, H., Pelillo, M.: Structured class-labels in random forests for semantic image labelling. In: ICCV (2011)
  2. Brostow, G.J., Shotton, J., Fauqueur, J., Cipolla, R.: Segmentation and Recognition Using Structure from Motion Point Clouds. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol.聽5302, pp. 44鈥?7. Springer, Heidelberg (2008) CrossRef
  3. Tighe, J., Lazebnik, S.: SuperParsing: Scalable Nonparametric Image Parsing with Superpixels. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol.聽6315, pp. 352鈥?65. Springer, Heidelberg (2010) CrossRef
  4. He, X., Zemel, R., Carreira-Perpinan, M.: Multiscale conditional random fields for image labeling. In: CVPR (2004)
  5. Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: / textonBoost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol.聽3951, pp. 1鈥?5. Springer, Heidelberg (2006) CrossRef
  6. Kohli, P., Ladicky, L., Torr, P.: Robust higher order potentials for enforcing label consistency. In: CVPR (2008)
  7. Galleguillos, C., Rabinovich, A., Belongie, S.: Object categorization using co-occurrence, location and appearance. In: CVPR (2008)
  8. Ladicky, L., Russell, C., Kohli, P., Torr, P.H.S.: Graph Cut Based Inference with Co-occurrence Statistics. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol.聽6315, pp. 239鈥?53. Springer, Heidelberg (2010) CrossRef
  9. Gonfaus, J., Boix, X., van de Weijer, J., Bagdanov, A., Serrat, J., Gonzandlez, J.: Harmony potentials for joint classification and segmentation. In: CVPR (2010)
  10. Torralba, A., Murphy, K., Freeman, W., Rubin, M.: Context-based vision system for place and object recognition. In: ICCV (2003)
  11. Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: ICCV (2007)
  12. Toyoda, T., Hasegawa, O.: Random field model for integration of local information and global information. TPAMI聽30 (2008)
  13. Ladick媒, 慕., Sturgess, P., Alahari, K., Russell, C., Torr, P.H.S.: What, Where and How Many? Combining Object Detectors and CRFs. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol.聽6314, pp. 424鈥?37. Springer, Heidelberg (2010) CrossRef
  14. Russell, B.C., Torralba, A., Liu, C., Fergus, R., Freeman, W.T.: Object recognition by scene alignment. In: NIPS (2007)
  15. Liu, C., Yuen, J., Torralba, A.: Nonparametric scene parsing via label transfer. TPAMI聽33 (2011)
  16. Socher, R., Lin, C.C.Y., Ng, A.Y., Manning, C.D.: Parsing natural scenes and natural language with recursive neural networks. In: ICML (2011)
  17. Huang, Q., Han, M., Wu, B., Ioffe, S.: A hierarchical conditional random field model for labeling and segmenting images of street scenes. In: CVPR (2011)
  18. Arora, S., Hazan, E., Kale, S.: The multiplicative weights update method: a meta algorithm and applications. Technical report, Princeton University (2005)
  19. Kumar, N., Zhang, L., Nayar, S.K.: What Is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images? In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol.聽5303, pp. 364鈥?78. Springer, Heidelberg (2008) CrossRef
  20. Andoni, A., Indyk, P.: Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. Commun. ACM
  21. Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: A randomized correspondence algorithm for structural image editing. ACM Transactions on Graphics, Proc. SIGGRAPH (2009)
  
• 作者单位：Yiqing Yang (21)
  Zhouyuan Li (21)
  Li Zhang (21)
  Christopher Murphy (22)
  Jim Ver Hoeve (21)
  Hongrui Jiang (21)
  
  21. University of Wisconsin-Madison, USA
  22. University of California, Davis, USA
  

文摘

In this paper we introduce the concept of local label descriptor, which is a concatenation of label histograms for each cell in a patch. Local label descriptors alleviate the label patch misalignment issue in combining structured label predictions for semantic image labeling. Given an input image, we solve for a label map whose local label descriptors can be approximated as a sparse convex combination of exemplar label descriptors in the training data, where the sparsity is regularized by the similarity measure between the local feature descriptor of the input image and that of the exemplars in the training data set. Low-level image over-segmentation can be incorporated into our formulation to improve efficiency. Our formulation and algorithm compare favorably with the baseline method on the CamVid and Barcelona datasets.