Skip to main content
SpringerLink
Log in

Training Interpretable Convolutional Neural Networks by Differentiating Class-Specific Filters

  • Conference paper
  • First Online:
Computer Vision – ECCV 2020 (ECCV 2020)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12347))

Included in the following conference series:

Abstract

Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as “black-box” and lack of interpretability. One main reason is due to the filter-class entanglement – an intricate many-to-many correspondence between filters and classes. Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model. In contrast, we focus on alleviating filter-class entanglement during training. Inspired by cellular differentiation, we propose a novel strategy to train interpretable CNNs by encouraging class-specific filters, among which each filter responds to only one (or few) class. Concretely, we design a learnable sparse Class-Specific Gate (CSG) structure to assign each filter with one (or few) class in a flexible way. The gate allows a filter’s activation to pass only when the input samples come from the specific class. Extensive experiments demonstrate the fabulous performance of our method in generating a sparse and highly class-related representation of the input, which leads to stronger interpretability. Moreover, comparing with the standard training strategy, our model displays benefits in applications like object localization and adversarial sample detection. Code link: https://github.com/hyliang96/CSGCNN.

H. Liang and Z. Ouyang—contributed equally.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    \(\text {CE}(y||\tilde{{y}}^G_\theta )=- \frac{1}{|D|}\sum _{(x,y)\in D} \log ( (\tilde{{y}}^G_\theta )_y )\), where \(\tilde{{y}}^G_\theta \) is a predicted probability vector.

References

  1. Bai, J., Li, Y., Li, J., Jiang, Y., Xia, S.: Rectified decision trees: Towards interpretability, compression and empirical soundness. arXiv preprint arXiv:1903.05965 (2019)

  2. Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6541–6549 (2017)

    Google Scholar 

  3. Bojarski, M., et al.: Explaining how a deep neural network trained with end-to-end learning steers a car. arXiv preprint arXiv:1704.07911 (2017)

  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. Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)

    Article  Google Scholar 

  6. Burgess, C.P., et al.: Understanding disentangling in \(\beta \)-vae. arXiv preprint arXiv:1804.03599 (2018)

  7. Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: S&P (2017)

    Google Scholar 

  8. Caruana, R., et al.: Intelligible models for healthcare: predicting pneumonia risk and hospital 30-day readmission. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1721–1730. ACM (2015)

    Google Scholar 

  9. Chen, T.Q., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. In: Advances in Neural Information Processing Systems, pp. 2610–2620 (2018)

    Google Scholar 

  10. Chen, X., et al.: Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172–2180 (2016)

    Google Scholar 

  11. Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2009)

    Google Scholar 

  12. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2010 (VOC2010) Results. http://www.pascal-network.org/challenges/VOC/voc2010/workshop/index.html

  13. Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)

    Google Scholar 

  14. Gonzalez-Garcia, A., Modolo, D., Ferrari, V.: Do semantic parts emerge in convolutional neural networks? Int. J. Comput. Vis. 126(5), 476–494 (2018)

    Article  MathSciNet  Google Scholar 

  15. Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2014)

    Google Scholar 

  16. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)

    Google Scholar 

  17. 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 

  18. Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., Lerchner, A.: beta-vae: learning basic visual concepts with a constrained variational framework. Int. Conf. Learn. Represent. 2(5), 6 (2017)

    Google Scholar 

  19. Jiang, Z., Wang, Y., Davis, L., Andrews, W., Rozgic, V.: Learning discriminative features via label consistent neural network. In: 2017 IEEE Winter Conference on Applications of Computer Vision, pp. 207–216. IEEE (2017)

    Google Scholar 

  20. Kim, H., Mnih, A.: Disentangling by factorising. arXiv preprint arXiv:1802.05983 (2018)

  21. Kingma, D.P., Welling, M.: Stochastic gradient VB and the variational auto-encoder. In: International Conference on Learning Representations (2014)

    Google Scholar 

  22. Krizhevsky, A., et al.: Learning multiple layers of features from tiny images. Technical report TR-2009 (2009)

    Google Scholar 

  23. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

    Google Scholar 

  24. Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. arXiv preprint arXiv:1711.00848 (2017)

  25. Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations. arXiv preprint arXiv:1811.12359 (2018)

  26. Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)

  27. Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5188–5196 (2015)

    Google Scholar 

  28. Martinez, B., Modolo, D., Xiong, Y., Tighe, J.: Action recognition with spatial-temporal discriminative filter banks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5482–5491 (2019)

    Google Scholar 

  29. Mordvintsev, A., Olah, C., Tyka, M.: Inceptionism: going deeper into neural networks (2015). https://research.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html

  30. Olah, C., et al.: The building blocks of interpretability. Distill (2018). https://doi.org/10.23915/distill.00010. https://distill.pub/2018/building-blocks

  31. Prakash, A., Storer, J., Florencio, D., Zhang, C.: RePr: improved training of convolutional filters. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10666–10675 (2019)

    Google Scholar 

  32. Ross, B.C.: Mutual information between discrete and continuous data sets. PloS one 9(2), e87357 (2014)

    Article  Google Scholar 

  33. Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems, pp. 3856–3866 (2017)

    Google Scholar 

  34. Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)

  35. Smith, A.G., et al.: Inhibition of pluripotential embryonic stem cell differentiation by purified polypeptides. Nature 336(6200), 688–690 (1988)

    Article  Google Scholar 

  36. Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)

  37. Thomas, V., et al.: Disentangling the independently controllable factors of variation by interacting with the world. arXiv preprint arXiv:1802.09484 (2018)

  38. Wang, Y., Morariu, V.I., Davis, L.S.: Learning a discriminative filter bank within a cnn for fine-grained recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4148–4157 (2018)

    Google Scholar 

  39. Wang, Y., Su, H., Zhang, B., Hu, X.: Interpret neural networks by identifying critical data routing paths. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8906–8914 (2018)

    Google Scholar 

  40. 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_53

    Chapter  Google Scholar 

  41. Zhang, Q., Cao, R., Wu, Y.N., Zhu, S.C.: Mining object parts from CNNS via active question-answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 346–355 (2017)

    Google Scholar 

  42. Zhang, Q., Cao, R., Shi, F., Wu, Y.N., Zhu, S.C.: Interpreting CNN knowledge via an explanatory graph. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)

    Google Scholar 

  43. Zhang, Q., Cao, R., Wu, Y.N., Zhu, S.C.: Growing interpretable part graphs on convnets via multi-shot learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)

    Google Scholar 

  44. Zhang, Q., et al.: Interactively transferring cnn patterns for part localization. arXiv preprint arXiv:1708.01783 (2017)

  45. Zhang, Q., Wu, Y.N., Zhu, S.C.: Interpretable convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8827–8836 (2018)

    Google Scholar 

  46. Zhang, Q., Yang, Y., Ma, H., Wu, Y.N.: Interpreting CNNS via decision trees. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6261–6270 (2019)

    Google Scholar 

  47. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)

    Google Scholar 

Download references

Acknowledgement

This work was supported by the National Key R&D Program of China (2017YFA0700904), NSFC Projects (61620106010, U19B2034, U1811461, U19A2081, 61673241, 61771273), Beijing NSF Project (L172037), PCL Future Greater-Bay Area Network Facilities for Large-scale Experiments and Applications (LZC0019), Beijing Academy of Artificial Intelligence (BAAI), Tsinghua-Huawei Joint Research Program, a grant from Tsinghua Institute for Guo Qiang, Tiangong Institute for Intelligent Computing, the JP Morgan Faculty Research Program, Microsoft Research Asia, Rejoice Sport Tech. co., LTD and the NVIDIA NVAIL Program with GPU/DGX Acceleration.

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, BNRist Center, Institute for AI, THBI Laboratory, Tsinghua University, Beijing, 100084, China

    Haoyu Liang, Hang Su, Jun Zhu & Bo Zhang

  2. Tsinghua SIGS, Shenzhen, 518055, China

    Zhihao Ouyang, Yuyuan Zeng & Shu-Tao Xia

  3. Peng Cheng Laboratory, University of Southern California, Los Angele, USA

    Yuyuan Zeng & Shu-Tao Xia

  4. ByteDance AI Lab, University of Southern California, Los Angele, USA

    Zhihao Ouyang

  5. Department of CS, University of Southern California, Los Angele, USA

    Zihao He

Authors
  1. Haoyu Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhihao Ouyang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuyuan Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hang Su
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zihao He
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shu-Tao Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Jun Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Bo Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Hang Su or Jun Zhu .

Editor information

Editors and Affiliations

  1. University of Oxford, Oxford, UK

    Andrea Vedaldi

  2. Graz University of Technology, Graz, Austria

    Horst Bischof

  3. University of Freiburg, Freiburg im Breisgau, Germany

    Thomas Brox

  4. University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Jan-Michael Frahm

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 356 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Liang, H. et al. (2020). Training Interpretable Convolutional Neural Networks by Differentiating Class-Specific Filters. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12347. Springer, Cham. https://doi.org/10.1007/978-3-030-58536-5_37

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-58536-5_37

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58535-8

  • Online ISBN: 978-3-030-58536-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation