Abstract
The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that humans cannot fully trust the predictions made by these models. To date, little work has been done on how to align the behaviors of deep learning models with human perception in order to train a human-understandable model. To fill this gap, we propose a new framework to train a deep neural network by incorporating the prior of human perception into the model learning process. Our proposed model mimics the process of perceiving conceptual parts from images and assessing their relative contributions towards the final recognition. The effectiveness of our proposed model is evaluated on two classical visual recognition tasks. The experimental results and analysis confirm our model is able to provide interpretable explanations for its predictions, but also maintain competitive recognition accuracy.
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
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. In: NeurIPS, pp. 9505–9515 (2018)
Biederman, I.: Recognition-by-components: a theory of human image understanding. Psychol. Rev. 94(2), 115 (1987)
Chang, D., et al.: The devil is in the channels: mutual-channel loss for fine-grained image classification. IEEE Trans. Image Process. 29, 4683–4695 (2020)
Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. In: WACV, pp. 839–847. IEEE (2018)
Dong, Y., Su, H., Zhu, J., Zhang, B.: Improving interpretability of deep neural networks with semantic information. In: CVPR, pp. 4306–4314 (2017)
Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017)
Ghorbani, A., Abid, A., Zou, J.: Interpretation of neural networks is fragile. In: AAAI, Vol. 33, No. 01, pp. 3681–3688 (2019)
Ghorbani, A., Wexler, J., Zou, J.Y., Kim, B.: Towards automatic concept-based explanations. In: NeurIPS, pp. 9273–9282 (2019)
Goodfellow, I.J., et al.: Challenges in representation learning: a report on three machine learning contests. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8228, pp. 117–124. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-42051-1_16
Hendricks, L.A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., Darrell, T.: Generating visual explanations. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 3–19. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_1
Huang, Z., Li, Y.: Interpretable and accurate fine-grained recognition via region grouping. In: CVPR, pp. 8662–8672 (2020)
Jacobs, R.A., et al.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79–87 (1991)
Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40, (2017)
Laugel, T., Lesot, M.J., Marsala, C., Renard, X., Detyniecki, M.: The dangers of post-hoc interpretability: unjustified counterfactual explanations. In: IJCAI, pp. 2801–2807. AAAI Press (2019)
Mordan, T., Thome, N., Henaff, G., Cord, M.: End-to-end learning of latent deformable part-based representations for object detection. Int. J. Compute. Vision 127(11–12), 1659–1679 (2019)
Paçacı, G., Johnson, D., McKeever, S., Hamfelt, A.: “Why did you do that?”: explaining black box models with inductive synthesis. In: ICCS, Faro, Algarve, Portugal (2019)
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you?: explaining the predictions of any classifier. In: SIGKDD, pp. 1135–1144. ACM (2016)
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: ICML, pp. 3145–3153. JMLR. org (2017)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: ICML, pp. 3319–3328. JMLR. org (2017)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset. Tech. Rep. CNS-TR-2011-001, Caltech (2011)
Wu, H., Wang, C., Yin, J., Lu, K., Zhu, L.: Sharing deep neural network models with interpretation. In: WWW, pp. 177–186. WWW Steering Committee (2018)
Zhang, H., et al.: SPDA-CNN: unifying semantic part detection and abstraction for fine-grained recognition. In: CVPR, pp. 1143–1152 (2016)
Zhang, Q., Nian Wu, Y., Zhu, S.C.: Interpretable convolutional neural networks. In: CVPR, pp. 8827–8836 (2018)
Acknowledgments
This work is partially supported by ARC under Grant DP180100106 and DP200101328. Xiaowei Zhou is supported by a Data61 Student Scholarship from CSIRO.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, X., Yin, J., Tsang, I., Wang, C. (2021). Human-Understandable Decision Making for Visual Recognition. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12714. Springer, Cham. https://doi.org/10.1007/978-3-030-75768-7_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-75768-7_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75767-0
Online ISBN: 978-3-030-75768-7
eBook Packages: Computer ScienceComputer Science (R0)