Abstract
Image-to-image translation has played an important role in enabling synthetic data for computer vision. However, if the source and target domains have a large semantic mismatch, existing techniques often suffer from source content corruption aka semantic flipping. To address this problem, we propose a new paradigm for image-to-image translation using Vector Symbolic Architectures (VSA), a theoretical framework which defines algebraic operations in a high-dimensional vector (hypervector) space. We introduce VSA-based constraints on adversarial learning for source-to-target translations by learning a hypervector mapping that inverts the translation to ensure consistency with source content. We show both qualitatively and quantitatively that our method improves over other state-of-the-art techniques.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmad, S., Hawkins, J.: Properties of sparse distributed representations and their application to hierarchical temporal memory. arXiv preprint arXiv:1503.07469 (2015)
Almahairi, A., Rajeshwar, S., Sordoni, A., Bachman, P., Courville, A.: Augmented cyclegan: Learning many-to-many mappings from unpaired data. In: International Conference on Machine Learning, pp. 195–204. PMLR (2018)
Benaim, S., Wolf, L.: One-sided unsupervised domain mapping. In: Advances in neural Information Processing Systems 30 (2017)
Bińkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans. arXiv preprint arXiv:1801.01401 (2018)
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)
Devaranjan, J., Kar, A., Fidler, S.: Meta-sim2: unsupervised learning of scene structure for synthetic data generation. In: European Conference on Computer Vision, pp. 715–733. Springer (2020). https://doi.org/10.1007/978-3-030-58520-4_42
Fu, H., Gong, M., Wang, C., Batmanghelich, K., Zhang, K., Tao, D.: Geometry-consistent generative adversarial networks for one-sided unsupervised domain mapping. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2427–2436 (2019)
Gayler, R.W.: Vector symbolic architectures answer jackendoff’s challenges for cognitive neuroscience. arXiv preprint cs/0412059 (2004)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems 27 (2014)
Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. In: International Conference on Machine Learning, pp. 1989–1998. PMLR (2018)
Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 172–189 (2018)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134 (2017)
Jia, Z., et al.: Semantically robust unpaired image translation for data with unmatched semantics statistics. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 14273–14283 (2021)
Kanerva, P.: Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors. Cogn. Comput. 1(2), 139–159 (2009). https://doi.org/10.1007/s12559-009-9009-8
Kar, A., et al: Meta-sim: learning to generate synthetic datasets. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4551–4560 (2019)
Kent, S., Olshausen, B.: A vector symbolic approach to scene transformation. Cognitive computational neuroscience (ccn 2017) (extended abstract) [link] (2017)
Kim, T., Cha, M., Kim, H., Lee, J.K., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. In: International Conference on Machine Learning, pp. 1857–1865. PMLR (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Kleyko, D., Rachkovskij, D.A., Osipov, E., Rahim, A.: A survey on hyperdimensional computing aka vector symbolic architectures, part ii: applications, cognitive models, and challenges. arXiv preprint arXiv:2112.15424 (2021)
Kleyko, D., Rachkovskij, D.A., Osipov, E., Rahimi, A.: A survey on hyperdimensional computing aka vector symbolic architectures, part i: models and data transformations. arXiv preprint arXiv:2111.06077 (2021)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25 (2012)
Lee, H.Y., Tseng, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Diverse image-to-image translation via disentangled representations. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 35–51 (2018)
Lim, J.H., Ye, J.C.: Geometric gan. arXiv preprint arXiv:1705.02894 (2017)
Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: Advances in Neural Information Processing Systems 30 (2017)
Montone, G., O’Regan, J.K., Terekhov, A.V.: Hyper-dimensional computing for a visual question-answering system that is trainable end-to-end. arXiv preprint arXiv:1711.10185 (2017)
Neubert, P., Schubert, S.: Hyperdimensional computing as a framework for systematic aggregation of image descriptors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16938–16947 (2021)
Neubert, P., Schubert, S., Protzel, P.: An introduction to hyperdimensional computing for robotics. KI-Künstliche Intelligenz 33(4), 319–330 (2019). https://doi.org/10.1007/s13218-019-00623-z
Osipov, E., et al.: Hyperseed: unsupervised learning with vector symbolic architectures. arXiv preprint arXiv:2110.08343 (2021)
Park, T., Efros, A.A., Zhang, R., Zhu, J.Y.: Contrastive learning for unpaired image-to-image translation. In: European Conference on Computer Vision, pp. 319–345. Springer (2020). https://doi.org/10.1007/978-3-030-58545-7_19
Prakash, A., Debnath, S., Lafleche, J.F., Cameracci, E., Birchfield, S., Law, M.T., et al.: Self-supervised real-to-sim scene generation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 16044–16054 (2021)
Purdy, S.: Encoding data for htm systems. arXiv preprint arXiv:1602.05925 (2016)
Richter, S.R., AlHaija, H.A., Koltun, V.: Enhancing photorealism enhancement. arXiv preprint arXiv:2105.04619 (2021)
Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: Ground truth from computer games. In: European Conference on Computer Vision, pp. 102–118. Springer (2016). https://doi.org/10.1007/978-3-319-46475-6_7
Schlegel, K., Neubert, P., Protzel, P.: A comparison of vector symbolic architectures. Artif. Intell. Rev. 1–33 (2021). https://doi.org/10.1007/s10462-021-10110-3
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Yi, Z., Zhang, H., Tan, P., Gong, M.: Dualgan: unsupervised dual learning for image-to-image translation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2849–2857 (2017)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)
Acknowledgments
We thank Mihir Jain, Shingo Takagi, Patrick Rodriguez, Sarah Watson, Zijian He, Peizhao Zhang, and Tao Xu for their helpful feedback.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Theiss, J., Leverett, J., Kim, D., Prakash, A. (2022). Unpaired Image Translation via Vector Symbolic Architectures. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13681. Springer, Cham. https://doi.org/10.1007/978-3-031-19803-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-19803-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19802-1
Online ISBN: 978-3-031-19803-8
eBook Packages: Computer ScienceComputer Science (R0)