“A scalable active framework for region annotation in 3D shape collections” by Yi, Kim, Ceylan, Shen, Yan, et al. …
Conference:
Type(s):
Title:
- A scalable active framework for region annotation in 3D shape collections
Session/Category Title: Shape Semantics
Presenter(s)/Author(s):
Abstract:
Large repositories of 3D shapes provide valuable input for data-driven analysis and modeling tools. They are especially powerful once annotated with semantic information such as salient regions and functional parts. We propose a novel active learning method capable of enriching massive geometric datasets with accurate semantic region annotations. Given a shape collection and a user-specified region label our goal is to correctly demarcate the corresponding regions with minimal manual work. Our active framework achieves this goal by cycling between manually annotating the regions, automatically propagating these annotations across the rest of the shapes, manually verifying both human and automatic annotations, and learning from the verification results to improve the automatic propagation algorithm. We use a unified utility function that explicitly models the time cost of human input across all steps of our method. This allows us to jointly optimize for the set of models to annotate and for the set of models to verify based on the predicted impact of these actions on the human efficiency. We demonstrate that incorporating verification of all produced labelings within this unified objective improves both accuracy and efficiency of the active learning procedure. We automatically propagate human labels across a dynamic shape network using a conditional random field (CRF) framework, taking advantage of global shape-to-shape similarities, local feature similarities, and point-to-point correspondences. By combining these diverse cues we achieve higher accuracy than existing alternatives. We validate our framework on existing benchmarks demonstrating it to be significantly more efficient at using human input compared to previous techniques. We further validate its efficiency and robustness by annotating a massive shape dataset, labeling over 93,000 shape parts, across multiple model classes, and providing a labeled part collection more than one order of magnitude larger than existing ones.
References:
1. Boyko, A., and Funkhouser, T. 2014. Cheaper by the dozen: Group annotation of 3D data. UIST.
2. Branson, S., Perona, P., and Belongie, S. 2011. Strong supervision from weak annotation: Interactive training of deformable part models. In IEEE ICCV.
3. Branson, S., Van Horn, G., Wah, C., Perona, P., and Belongie, S. 2014. The ignorant led by the blind: A hybrid human-machine vision system for fine-grained categorization. IJCV 108, 1–2, 3–29.
4. Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., Xiao, J., Yi, L., and Yu, F. 2015. ShapeNet: An Information-Rich 3D Model Repository. Tech. Rep. arXiv:1512.03012 {cs.GR}.
5. Chaudhuri, S., Kalogerakis, E., Guibas, L., and Koltun, V. 2011. Probabilistic reasoning for assembly-based 3D modeling. ACM SIGGRAPH, 35:1–35:10.
6. Chen, D.-Y., Tian, X.-P., Shen, Y.-T., and Ouhyoung, M. 2003. On visual similarity based 3d model retrieval. Eurographics 22, 3, 223–232. Cross Ref
7. Chen, X., Golovinskiy, A., and Funkhouser, T. 2009. A benchmark for 3D mesh segmentation. ACM SIGGRAPH 28, 3.
8. Guo, K., Zou, D., and Chen, X. 2015. 3D mesh labeling via deep convolutional neural networks. ACM TOG 35, 1.
9. Hu, R., Fan, L., and Liu, L. 2012. Co-segmentation of 3d shapes via subspace clustering. CGF 31, 5 (Aug.), 1703–1713.
10. Huang, Q., Koltun, V., and Guibas, L. 2011. Joint shape segmentation with linear programming. In ACM SIGGRAPH Asia, 125:1–125:12.
11. Huang, Q.-X., Su, H., and Guibas, L. 2013. Fine-grained semi-supervised labeling of large shape collections. SIGGRAPH Asia 32, 6, 190:1–190:10.
12. Huang, Q., Wang, F., and Guibas, L. 2014. Functional map networks for analyzing and exploring large shape collections. SIGGRAPH 33, 4, 36:1–36:11.
13. Kalogerakis, E., Hertzmann, A., and Singh, K. 2010. Learning 3D mesh segmentation and labeling. In ACM SIGGRAPH, 102:1–102:12.
14. Kalogerakis, E., Chaudhuri, S., Koller, D., and Koltun, V. 2012. A probabilistic model for component-based shape synthesis. SIGGRAPH.
15. Kim, V. G., Li, W., Mitra, N., DiVerdi, S., and Funkhouser, T. 2012. Exploring collections of 3D models using fuzzy correspondences. SIGGRAPH.
16. Kim, V. G., Chaudhuri, S., Guibas, L., and Funkhouser, T. 2014. Shape2Pose: Human-Centric Shape Analysis. SIGGRAPH 33, 4.
17. Leordeanu, M., and Hebert, M. 2005. A spectral technique for correspondence problems using pairwise constraints. In ICCV, vol. 2, IEEE, 1482–1489.
18. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. 2014. Microsoft coco: Common objects in context. ECCV.
19. Lv, J., Chen, X., Huang, J., and Bao, H. 2012. Semi-supervised mesh segmentation and labeling. CGF 31.
20. Makadia, A., and Yumer, M. E. 2014. Learning 3d part detection from sparsely labeled data. In 3DV.
21. Rubinstein, M., Liu, C., and Freeman, W. T. 2012. Annotation propagation in large image databases via dense image correspondence. ECCV, 85–99.
22. Russakovsky, O., Li, L.-J., and Fei-Fei, L. 2015. Best of both worlds: human-machine collaboration for object annotation. In IEEE CVPR.
23. Shamir, A. 2008. A survey on mesh segmentation techniques. Computer Graphics Forum 27, 6, 1539–1556. Cross Ref
24. Shu, Z., Qi, C., Xin, S., Hu, C., Wang, L., Zhang, Y., and Liu, L. 2016. Unsupervised 3d shape segmentation and co-segmentation via deep learning. Comp. Aided Geom. Des. 43.
25. Sidi, O., van Kaick, O., Kleiman, Y., Zhang, H., and Cohen-Or, D. 2011. Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering. ACM SIGGRAPH Asia 30, 6, 126:1–126:9.
26. Su, H., Deng, J., and Fei-Fei, L. 2012. Crowdsourcing annotations for visual object detection. In Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence.
27. Sung, M., Kim, V. G., Angst, R., and Guibas, L. 2015. Data-driven structural priors for shape completion. SIGGRAPH Asia.
28. Trimble, 2015. Trimble 3D warehouse.
29. Vezhnevets, A., Buhmann, J., and Ferrari, V. 2012. Active learning for semantic segmentation with expected change. In IEEE CVPR, 3162–3169.
30. Vijayanarasimhan, S., and Grauman, K. 2008. Multi-level active prediction of useful image annotations for recognition. In NIPS, 1705–1712.
31. Wang, Y., Asafi, S., van Kaick, O., Zhang, H., Cohen-Or, D., and Chenand, B. 2012. Active co-analysis of a set of shapes. SIGGRAPH Asia.
32. Weinberger, K. Q., Blitzer, J., and Saul, L. K. 2005. Distance metric learning for large margin nearest neighbor classification. In NIPS, 1473–1480.
33. Wu, Z., Shou, R., Wang, Y., and Liu, X. 2014. Interactive shape co-segmentation via label propagation. CAD/Graphics.
34. Xie, Z., Xu, K., Liu, L., and Xiong, Y. 2014. 3d shape segmentation and labeling via extreme learning machine. SGP.
35. Zadrozny, B., and Elkan, C. 2002. Transforming classifier scores into accurate multiclass probability estimates. In SIGKDD Int. Conf. on Knowledge Discovery and Data Mining.
