Abstract
Disentangled and invariant representations are two critical goals of representation learning and many approaches have been proposed to achieve either one of them. However, those two goals are actually complementary to each other so that we propose a framework to accomplish both of them simultaneously. We introduce a weakly supervised signal to learn disentangled representation which consists of three splits containing predictive, known nuisance and unknown nuisance information respectively. Furthermore, we incorporate contrastive method to enforce representation invariance. Experiments shows that the proposed method outperforms state-of-the-art (SOTA) methods on four standard benchmarks and shows that the proposed method can have better adversarial defense ability comparing to other methods without adversarial training.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives (2014)
Burgess, C., Kim, H.: 3D shapes dataset (2018). https://github.com/deepmind/3dshapes-dataset/
Burgess, C.P., et al.: Understanding disentangling in \(\beta \)-VAE (2018)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP) (2017)
Castro, P.S.: Scalable methods for computing state similarity in deterministic Markov decision processes. In: AAAI (2020)
Chen, J., Konrad, J., Ishwar, P.: A cyclically-trained adversarial network for invariant representation learning. In: CVPR Workshops (2020)
Chen, R.T.Q., Li, X., Grosse, R., Duvenaud, D.: Isolating sources of disentanglement in variational autoencoders (2019)
Eastwood, C., Williams, C.K.I.: A framework for the quantitative evaluation of disentangled representations. In: ICLR (2018). https://openreview.net/forum?id=By-7dz-AZ
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096–2130 (2016)
Gondal, M.W., et al.: On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset (2019)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples (2014). http://arxiv.org/abs/1412.6572, cite arxiv:1412.6572
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015)
Higgins, I., et al.: \(\beta \)-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)
Jaiswal, A., Wu, R.Y., Abd-Almageed, W., Natarajan, P.: Unsupervised adversarial invariance. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Khosla, P., et al.: Supervised contrastive learning. CoRR abs/2004.11362 (2020). https://arxiv.org/abs/2004.11362
Kim, H., Mnih, A.: Disentangling by factorising. In: ICML (2018). http://proceedings.mlr.press/v80/kim18b.html
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)
Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. In: ICLR (2018)
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial machine learning at scale. CoRR abs/1611.01236 (2016). http://arxiv.org/abs/1611.01236
LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http://yann.lecun.com/exdb/mnist/
Li, Y., Swersky, K., Zemel, R.: Learning unbiased features. arXiv preprint arXiv:1412.5244 (2014)
Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations (2019)
Locatello, F., Poole, B., Raetsch, G., Schölkopf, B., Bachem, O., Tschannen, M.: Weakly-supervised disentanglement without compromises. In: ICML (2020). http://proceedings.mlr.press/v119/locatello20a.html
Locatello, F., et al.: Disentangling factors of variations using few labels. In: ICLR (2020). https://openreview.net/forum?id=SygagpEKwB
Louizos, C., Swersky, K., Li, Y., Welling, M., Zeme, R.: The variational fair autoencoder. In: ICLR (2016)
Moyer, D., Gao, S., Brekelmans, R., Galstyan, A., Ver Steeg, G.: Invariant representations without adversarial training. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks. In: ICLR (2020). https://openreview.net/forum?id=ryxGuJrFvS
Sanchez, E.H., Serrurier, M., Ortner, M.: Learning disentangled representations via mutual information estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 205–221. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58542-6_13
van Steenkiste, S., Locatello, F., Schmidhuber, J., Bachem, O.: Are disentangled representations helpful for abstract visual reasoning? CoRR abs/1905.12506 (2019). http://arxiv.org/abs/1905.12506
Suter, R., Đorđe Miladinović, Schölkopf, B., Bauer, S.: Robustly disentangled causal mechanisms: validating deep representations for interventional robustness (2019)
Wang, F., Liu, H.: Understanding the behaviour of contrastive loss. In: CVPR (2021)
Xie, Q., Dai, Z., Du, Y., Hovy, E., Neubig, G.: Controllable invariance through adversarial feature learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Acknowledgement
This research is based upon work supported by the Defense Advanced Research Projects Agency (DARPA), under cooperative agreement number HR00112020009. The views and conclusions contained herein should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of DARPA or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright notation thereon.
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
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, J., Xie, H., Abd-Almageed, W. (2023). Weakly Supervised Invariant Representation Learning via Disentangling Known and Unknown Nuisance Factors. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13808. Springer, Cham. https://doi.org/10.1007/978-3-031-25085-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-25085-9_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25084-2
Online ISBN: 978-3-031-25085-9
eBook Packages: Computer ScienceComputer Science (R0)