Abstract
In this chapter, we introduce Network Dissection (The complete paper and code are available at http://netdissect.csail.mit.edu), a general framework to quantify the interpretability of the units inside a deep convolutional neural networks (CNNs). We compare the different vocabularies of interpretable units as concept detectors emerged from the networks trained to solve different supervised learning tasks such as object recognition on ImageNet and scene classification on Places. The network dissection is further applied to analyze how the units acting as semantic detectors grow and evolve over the training iterations both in the scenario of the train-from-scratch and in the stage of the fine-tuning between data sources. Our results highlight that interpretability is an important property of deep neural networks that provides new insights into their hierarchical structure.
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
References
Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: Computer Vision and Pattern Recognition (2017)
Bell, S., Bala, K., Snavely, N.: Intrinsic images in the wild. ACM Trans. Graph. 33(4), 159 (2014)
Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., Yuille, A.: Detect what you can: detecting and representing objects using holistic models and body parts. In: Proceeding CVPR (2014)
Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings CVPR (2014)
Jolliffe, I.: Principal Component Analysis. Wiley Online Library, Hoboken (2002)
van der Maaten, L., Hinton, G.: Visualizing data using t-SNE: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. Proceedings CVPR (2015)
Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings CVPR (2014)
Nguyen, A., Dosovitskiy, A., Yosinski, J., Brox, T., Clune, J.: Synthesizing the preferred inputs for neurons in neural networks via deep generator networks. In: Advances in Neural Information Processing Systems (2016)
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., Müller, K.R.: Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Netw. Learn. Syst. 28(11), 2660–2673 (2017)
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 ICCV (2017)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: International Conference on Learning Representations Workshop (2014)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Proceedings ECCV (2014)
Zhang, J., Bargal, S.A., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. Int. J. Comput. Vision 126(10), 1084–1102 (2018)
Zhou, B., Bau, D., Oliva, A., Torralba, A.: Interpreting deep visual representations via network dissection. IEEE Trans. Pattern Anal. Mach. Intell. (2018). https://doi.org/10.1109/TPAMI.2018.2858759
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. In: International Conference on Learning Representations (2015)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings CVPR (2016)
Zhou, B., Sun, Y., Bau, D., Torralba, A.: Interpretable basis decomposition for visual explanation. In: Proceedings ECCV (2018)
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: Proceedings CVPR (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Zhou, B., Bau, D., Oliva, A., Torralba, A. (2019). Comparing the Interpretability of Deep Networks via Network Dissection. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L., Müller, KR. (eds) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. Lecture Notes in Computer Science(), vol 11700. Springer, Cham. https://doi.org/10.1007/978-3-030-28954-6_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-28954-6_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-28953-9
Online ISBN: 978-3-030-28954-6
eBook Packages: Computer ScienceComputer Science (R0)