Advertisement

iCaps: An Interpretable Classifier via Disentangled Capsule Networks

Conference paper
  • 649 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12364)

Abstract

We propose an interpretable Capsule Network, \(\textit{iCaps}\), for image classification. A capsule is a group of neurons nested inside each layer, and the one in the last layer is called a class capsule, which is a vector whose norm indicates a predicted probability for the class. Using the class capsule, existing Capsule Networks already provide some level of interpretability. However, there are two limitations which degrade its interpretability: 1) the class capsule also includes classification-irrelevant information, and 2) entities represented by the class capsule overlap. In this work, we address these two limitations using a novel class-supervised disentanglement algorithm and an additional regularizer, respectively. Through quantitative and qualitative evaluations on three datasets, we demonstrate that the resulting classifier, \(\textit{iCaps}\), provides a prediction along with clear rationales behind it with no performance degradation.

Keywords

Capsule Networks Interpretable neural networks Class-supervised disentanglement Generative Adversarial Networks (GANs) 

Notes

Acknowledgments

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science and ICT) [2018R1A2B3001628], the Brain Korea 21 Plus Project in 2020, Samsung Advanced Institute of Technology and Institute for Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019-0-01367, BabyMind), and AIR Lab in Hyundai Motor Company through HMC-SNU AI Consortium Fund.

Supplementary material

504475_1_En_19_MOESM1_ESM.pdf (3.6 mb)
Supplementary material 1 (pdf 3734 KB)

References

  1. 1.
    Adebayo, J., Gilmer, J., Goodfellow, I., Kim, B.: Local explanation methods for deep neural networks lack sensitivity to parameter values. arXiv preprint arXiv:1810.03307 (2018)
  2. 2.
    Ahmed, K., Torresani, L.: STAR-Caps: capsule networks with straight-through attentive routing. In: Advances in Neural Information Processing Systems, pp. 9098–9107 (2019)Google Scholar
  3. 3.
    Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS ONE 10(7), e0130140 (2015)CrossRefGoogle Scholar
  4. 4.
    Bouchacourt, D., Tomioka, R., Nowozin, S.: Multi-level variational autoencoder: learning disentangled representations from grouped observations. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar
  5. 5.
    Chang, C.H., Creager, E., Goldenberg, A., Duvenaud, D.: Explaining image classifiers by counterfactual generation (2018)Google Scholar
  6. 6.
    Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., Su, J.K.: This looks like that: deep learning for interpretable image recognition. In: Advances in Neural Information Processing Systems, pp. 8928–8939 (2019)Google Scholar
  7. 7.
    Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172–2180 (2016)Google Scholar
  8. 8.
    Dabkowski, P., Gal, Y.: Real time image saliency for black box classifiers. In: Advances in Neural Information Processing Systems, pp. 6967–6976 (2017)Google Scholar
  9. 9.
    Denton, E.L., et al.: Unsupervised learning of disentangled representations from video. In: Advances in Neural Information Processing Systems, pp. 4414–4423 (2017)Google Scholar
  10. 10.
    Fong, R., Patrick, M., Vedaldi, A.: Understanding deep networks via extremal perturbations and smooth masks. arXiv preprint arXiv:1910.08485 (2019)
  11. 11.
    Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3429–3437 (2017)Google Scholar
  12. 12.
    Gabbay, A., Hoshen, Y.: Demystifying inter-class disentanglement. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=Hyl9xxHYPr
  13. 13.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  14. 14.
    Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)Google Scholar
  15. 15.
    Hahn, T., Pyeon, M., Kim, G.: Self-routing capsule networks. In: Advances in Neural Information Processing Systems, pp. 7656–7665 (2019)Google Scholar
  16. 16.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  17. 17.
    Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626–6637 (2017)Google Scholar
  18. 18.
    Higgins, I., et al.: Beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR, vol. 2, no. 5, p. 6 (2017)Google Scholar
  19. 19.
    Jeong, T., Lee, Y., Kim, H.: Ladder capsule network. In: International Conference on Machine Learning. pp, 3071–3079 (2019)Google Scholar
  20. 20.
    Jha, A.H., Anand, S., Singh, M., Veeravasarapu, V.S.R.: Disentangling factors of variation with cycle-consistent variational auto-encoders. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 829–845. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_49CrossRefGoogle Scholar
  21. 21.
    Kim, B., Gilmer, J., Wattenberg, M., Viégas, F.: TCAV: relative concept importance testing with linear concept activation vectors (2018)Google Scholar
  22. 22.
    Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: International Conference on Machine Learning, pp. 2668–2677 (2018)Google Scholar
  23. 23.
    Kim, H., Mnih, A.: Disentangling by factorising. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research. PMLR, Stockholmsmässan, Stockholm, Sweden, 10–15 July 2018, vol. 80, pp. 2649–2658 (2018)Google Scholar
  24. 24.
    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
  25. 25.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  26. 26.
    LeCun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004, vol. 2, pp. II-104. IEEE (2004)Google Scholar
  27. 27.
    Li, O., Liu, H., Chen, C., Rudin, C.: Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar
  28. 28.
    Lin, Z., Thekumparampil, K.K., Fanti, G., Oh, S.: InfoGAN-CR: disentangling generative adversarial networks with contrastive regularizers. arXiv preprint arXiv:1906.06034 (2019)
  29. 29.
    Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV), December 2015Google Scholar
  30. 30.
    Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)zbMATHGoogle Scholar
  31. 31.
    Melis, D.A., Jaakkola, T.: Towards robust interpretability with self-explaining neural networks. In: Advances in Neural Information Processing Systems, pp. 7775–7784 (2018)Google Scholar
  32. 32.
    Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)Google Scholar
  33. 33.
    Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2642–2651. JMLR. org (2017)Google Scholar
  34. 34.
    Petsiuk, V., Das, A., Saenko, K.: RISE: randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421 (2018)
  35. 35.
    Petzka, H., Fischer, A., Lukovnikov, D.: On the regularization of wasserstein GANs. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=B1hYRMbCW
  36. 36.
    Rajasegaran, J., Jayasundara, V., Jayasekara, S., Jayasekara, H., Seneviratne, S., Rodrigo, R.: DeepCaps: going deeper with capsule networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10725–10733 (2019)Google Scholar
  37. 37.
    Reed, S.E., Zhang, Y., Zhang, Y., Lee, H.: Deep visual analogy-making. In: Advances in Neural Information Processing Systems, pp. 1252–1260 (2015)Google Scholar
  38. 38.
    Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems, pp. 3856–3866 (2017)Google Scholar
  39. 39.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, vol. 3, pp. 32–36. IEEE (2004)Google Scholar
  40. 40.
    Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)Google Scholar
  41. 41.
    Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3145–3153. JMLR. org (2017)Google Scholar
  42. 42.
    Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
  43. 43.
    Smilkov, D., Thorat, N., Kim, B., Viégas, F., Wattenberg, M.: Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)
  44. 44.
    Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)
  45. 45.
    Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3319–3328. JMLR. org (2017)Google Scholar
  46. 46.
    Szabó, A., Hu, Q., Portenier, T., Zwicker, M., Favaro, P.: Challenges in disentangling independent factors of variation. arXiv preprint arXiv:1711.02245 (2017)
  47. 47.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10590-1_53CrossRefGoogle Scholar
  48. 48.
    Zintgraf, L.M., Cohen, T.S., Adel, T., Welling, M.: Visualizing deep neural network decisions: prediction difference analysis. arXiv preprint arXiv:1702.04595 (2017)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Electrical and Computer Engineering, ASRI, INMC, and Institute of Engineering ResearchSeoul National UniversitySeoulSouth Korea

Personalised recommendations