Alexandr Notchenko

Founder and AI advisor

Graph-Convolutional systems for Inverse Graphics

This architecture is able to learn topological and other latent features of spatial objects and condition distribution of graphical parametres on them, thus enabling reconstruction.

[code is not available publicly at the moment], [preprint in preparation]

Selected References

  1. Wu, Jiajun, Joshua B. Tenenbaum, and Pushmeet Kohli. “Neural scene de-rendering.” In Proc. CVPR, vol. 2. 2017.
  2. Ganin, Yaroslav, Tejas Kulkarni, Igor Babuschkin, S. M. Eslami, and Oriol Vinyals. “Synthesizing Programs for Images using Reinforced Adversarial Learning.” ICML 2018 NAMPI Workshop. 2018.
  3. Hua, Binh-Son, Minh-Khoi Tran, and Sai-Kit Yeung. “Pointwise convolutional neural networks.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 984-993. 2018.
  4. Kool, W. W. M., and M. Welling. “Attention Solves Your TSP.” arXiv preprint arXiv:1803.08475. 2018.
  5. Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. “Attention is all you need.” In Advances in Neural Information Processing Systems, pp. 5998-6008. 2017.

Status: Work in progress

   

Sparse 3D Convolutional Neural Networks for Large-Scale Shape Retrieval

The goal of the research was to combining two ideas:

  1. 3D Sparse Convolutional Neural Networks
  2. metric learning (particulary triplet learning)

to solve shape retieval problem.

[code] [arxiv] [publication]

Selected References

  1. A. M. Bronstein, M. M. Bronstein, L. J. Guibas, and M. Ovsjanikov. Shape google: Geometric words and expressions for invariant shape retrieval. ACM Transactions on Graphics (TOG), 30(1):1, 2011.
  2. B. Graham. Spatially-sparse convolutional neural networks. arXiv preprint arXiv:1409.6070, 2014.
  3. V. Hegde and R. Zadeh. Fusionnet: 3d object classification using multiple data representations. arXiv preprint arXiv:1607.05695, 2016.
  4. E. Hoffer and N. Ailon. Deep metric learning using triplet network. In International Workshop on Similarity-Based Pattern Recognition, pages 84–92. Springer, 2015.
  5. E. Johns, S. Leutenegger, and A. J. Davison. Pairwise decomposition of image sequences for active multi-view recognition. arXiv preprint arXiv:1605.08359, 2016.
  6. D. Maturana and S. Scherer. Voxnet: A 3d convolutional neural network for realtime object recognition. In Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on, pages 922–928. IEEE, 2015.
  7. N. Sedaghat, M. Zolfaghari, and T. Brox. Orientation-boosted voxel nets for 3d object recognition. arXiv preprint arXiv:1604.03351, 2016.
  8. H. Su, S. Maji, E. Kalogerakis, and E. G. Learned-Miller. Multi-view convolutional neural networks for 3d shape recognition. In Proc. ICCV, 2015.
  9. J. Wang, Y. Song, T. Leung, C. Rosenberg, J. Wang, J. Philbin, B. Chen, and Y. Wu. Learning fine-grained image similarity with deep ranking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1386–1393, 2014.
  10. Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang, X. Tang, and J. Xiao. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1912–1920, 2015.

Status: Finished