Abstract
In this paper we consider the problem of classifying shapes within a given category (e.g., chairs) into finer-grained classes (e.g., chairs with arms, rocking chairs, swivel chairs). We introduce a multi-label (i.e., shapes can belong to multiple classes) semi-supervised approach that takes as input a large shape collection of a given category with associated sparse and noisy labels, and outputs cleaned and complete labels for each shape. The key idea of the proposed approach is to jointly learn a distance metric for each class which captures the underlying geometric similarity within that class, e.g., the distance metric for swivel chairs evaluates the global geometric resemblance of chair bases. We show how to achieve this objective by first geometrically aligning the input shapes, and then learning the class-specific distance metrics by exploiting the feature consistency provided by this alignment. The learning objectives consider both labeled data and the mutual relations between the distance metrics. Given the learned metrics, we apply a graph-based semi-supervised classification technique to generate the final classification results.
In order to evaluate the performance of our approach, we have created a benchmark data set where each shape is provided with a set of ground truth labels generated by Amazon's Mechanical Turk users. The benchmark contains a rich variety of shapes in a number of categories. Experimental results show that despite this variety, given very sparse and noisy initial labels, the new method yields results that are superior to state-of-the-art semi-supervised learning techniques.
Supplemental Material
Available for Download
Supplemental material.
- Amit, Y., Fink, M., Srebro, N., and Ullman, S. 2007. Uncovering shared structures in multiclass classification. ICML '07, 17--24. Google ScholarDigital Library
- Baghshah, M. S., and Shouraki, S. B. 2009. Semi-supervised metric learning using pairwise constraints. IJCAI'09, 1217--1222. Google ScholarDigital Library
- Boyd, S., Parikh, N., Chu, E., Peleato, B., and Eckstein, J. 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3, 1 (Jan.), 1--122. Google ScholarDigital Library
- Candès, E. J., and Recht, B. 2009. Exact matrix completion via convex optimization. Found. Comput. Math. 9, 6 (Dec.), 717--772. Google ScholarDigital Library
- Chen, D.-Y., Tian, X.-P., Shen, Y.-T., and Ouhyoung, M. 2003. On visual similarity based 3d model retrieval. Comput. Graph. Forum 22, 3, 223--232.Google ScholarCross Ref
- Chen, G., Song, Y., Wang, F., and Zhang, C. 2008. Semi-supervised multi-label learning by solving a sylvester equation. In SDM, SIAM, 410--419.Google Scholar
- Coifman, R. R., Lafon, S., Lee, A. B., Maggioni, M., Warner, F., and Zucker, S. 2005. Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps. In PNAS, 7426--7431.Google Scholar
- Crandall, D., Owens, A., Snavely, N., and Huttenlocher, D. 2011. Discrete-continuous optimization for large-scale structure from motion. CVPR '11, 3001--3008. Google ScholarDigital Library
- da Fontoura Costa, L., and Cesar Jr., R. M. 2009. Shape Classification and Analysis: Theory and Practice, 2nd ed. CRC Press, Inc., Boca Raton, FL, USA. Google ScholarDigital Library
- Deng, J., Krause, J., and Fei-Fei, L. 2013. Fine-grained crowd-sourcing for fine-grained recognition. In CVPR'13. Google ScholarDigital Library
- Fergus, R., Weiss, Y., and Torralba, A. 2009. Semi-supervised learning in gigantic image collections. In NIPS, 522--530.Google Scholar
- Hoi, S. C., Liu, W., and Chang, S.-F. 2010. Semi-supervised distance metric learning for collaborative image retrieval and clustering. ACM Trans. Multimedia Comput. Commun. Appl. 6, 3 (Aug.), 18:1--18:26. Google ScholarDigital Library
- Holland, P. W., and Welsch, R. E. 1977. Robust regression using iteratively reweighted least-squares. Communications in Statistics: Theory and Methods A6, 813--827.Google ScholarCross Ref
- Huang, Q.-X., Zhang, G.-X., Gao, L., Hu, S.-M., Butscher, A., and Guibas, L. 2012. An optimization approach for extracting and encoding consistent maps in a shape collection. ACM Trans. Graph. 31, 6 (Nov.), 167:1--167:11. Google ScholarDigital Library
- Huber, D. 2002. Automatic Three-dimensional Modeling from Reality. PhD thesis, Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. Google ScholarDigital Library
- Johnson, A. E., and Hebert, M. 1999. Using spin images for efficient object recognition in cluttered 3d scenes. IEEE Trans. Pattern Anal. Mach. Intell. 21, 5 (May), 433--449. Google ScholarDigital Library
- Kalogerakis, E., Chaudhuri, S., Koller, D., and Koltun, V. 2012. A probabilistic model for component-based shape synthesis. ACM Trans. Graph. 31, 4 (July), 55:1--55:11. Google ScholarDigital Library
- Kazhdan, M., Funkhouser, T., and Rusinkiewicz, S. 2003. Rotation invariant spherical harmonic representation of 3d shape descriptors. SGP '03, 156--164. Google ScholarDigital Library
- Kim, V. G., Li, W., Mitra, N. J., DiVerdi, S., and Funkhouser, T. 2012. Exploring collections of 3d models using fuzzy correspondences. ACM Trans. Graph. 31, 4 (July), 54:1--54:11. Google ScholarDigital Library
- Kim, V. G., Li, W., Mitra, N. J., Chaudhuri, S., DiVerdi, S., and Funkhouser, T. 2013. Learning part-based templates from large collections of 3d shapes. ACM Trans. Graph. 32, 4 (July), 70:1--70:12. Google ScholarDigital Library
- Leordeanu, M., and Hebert, M. 2006. Efficient map approximation for dense energy functions. ICML '06, 545--552. Google ScholarDigital Library
- Li, H., Sumner, R. W., and Pauly, M. 2008. Global correspondence optimization for non-rigid registration of depth scans. In SGP, 1421--1430. Google ScholarDigital Library
- Liu, W., Wang, J., and Chang, S.-F. 2012. Robust and scalable graph-based semisupervised learning. Proceedings of the IEEE 100, 9, 2624--2638.Google ScholarCross Ref
- Loeff, N., Farhadi, A., Endres, I., and Forsyth, D. 2009. Unlabeled data improves word prediction. In ICCV'09, 956--962.Google Scholar
- Miller, G. A. 1995. Wordnet: A lexical database for english. Communications of the ACM 38, 39--41. Google ScholarDigital Library
- Osada, R., Funkhouser, T., Chazelle, B., and Dobkin, D. 2002. Shape distributions. ACM Trans. Graph. 21 (October), 807--832. Google ScholarDigital Library
- Sederberg, T. W., and Parry, S. R. 1986. Free-form deformation of solid geometric models. SIGGRAPH '86, 151--160. Google ScholarDigital Library
- Shi, J., and Malik, J. 2000. Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22 (August), 888--905. Google ScholarDigital Library
- Tsoumakas, G., and Katakis, I. 2007. Multi-label classification: An overview. Int J Data Ware. and Mining 2007, 1--13.Google Scholar
- Wang, Y., Asafi, S., van Kaick, O., Zhang, H., Cohen-Or, D., and Chen, B. 2012. Active co-analysis of a set of shapes. ACM Trans. Graph. 31, 6, 165. Google ScholarDigital Library
- Xu, K., Li, H., Zhang, H., Cohen-Or, D., Xiong, Y., and Cheng, Z.-Q. 2010. Style-content separation by anisotropic part scales. SIGGRAPH ASIA '10, 184:1--184:10. Google ScholarDigital Library
- Yang, L., and Jin, R. 2006. Distance metric learning: A comprehensive survey.Google Scholar
- Yao, B., Khosla, A., and Fei-Fei, L. 2011. Combining randomization and discrimination for fine-grained image categorization. In CVPR '11, 1577--1584. Google ScholarDigital Library
- Zhu, X. 2006. Semi-supervised learning literature survey. Computer Sciences TR 1530, University of Wisconsin Madison.Google Scholar
Index Terms
- Fine-grained semi-supervised labeling of large shape collections
Recommendations
Semi-supervised Multi-Label Topic Models for Document Classification and Sentence Labeling
CIKM '16: Proceedings of the 25th ACM International on Conference on Information and Knowledge ManagementExtracting parts of a text document relevant to a class label is a critical information retrieval task. We propose a semi-supervised multi-label topic model for jointly achieving document and sentence-level class inferences. Under our model, each ...
Unsupervised Selective Labeling for More Effective Semi-supervised Learning
Computer Vision – ECCV 2022AbstractGiven an unlabeled dataset and an annotation budget, we study how to selectively label a fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled dataset is most effective. We focus on selecting the right data ...
Bidirectional Semi-supervised learning with graphs
ECMLPKDD'12: Proceedings of the 2012th European Conference on Machine Learning and Knowledge Discovery in Databases - Volume Part IIWe present a machine learning task, which we call bidirectional semi-supervised learning, where label-only samples are given as well as labeled and unlabeled samples. A label-only sample contains the label information of the sample but not the feature ...
Comments