Abstract
Deep convolutional neural networks (CNNs) are the dominant technology in computer vision today. Unfortunately, it’s not clear how different from each other the best CNNs really are. This paper measures the similarity between two well-known CNNs, Inception and ResNet, in terms of the features they extract from images. We find that Inception’s features can be well approximated as an affine transformation of ResNet’s features and vice-versa.
The similarity between Inception and ResNet features is surprising. Convolutional neural networks learn complex non-linear features of images, and the architectural differences between the systems suggest that these functions should take different forms. Instead, they seem to have converged on similar solutions. This suggests that the selection of the training set may be more important than the selection of the convolutional architecture.
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
Bau D, Zhou B, Khosla A, Oliva A, Torralba A (2017) Network dissection: quantifying interpretability of deep visual representations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6541–6549
Dosovitskiy A, Brox T (2016) Inverting visual representations with convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4829–4837
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European conference on computer vision. Springer, pp 630–645 (2016)
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167
Kornblith S, Shlens, J, Le QV (2018) Do better imagenet models transfer better? arXiv preprint arXiv:1805.08974
Lenc K, Vedaldi A (2019) Understanding image representations by measuring their equivariance and equivalence. Int J Comput Vis 127(5):456–476. https://doi.org/10.1007/s11263-018-1098-y
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252
Silberman N, Guadarrama S (2016) Tensorflow-slim image classification model library. https://github.com/tensorflow/models/tree/master/research/slim
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence (2017)
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
McNeely-White, D.G., Beveridge, J.R., Draper, B.A. (2020). Inception and ResNet: Same Training, Same Features. In: Samsonovich, A. (eds) Biologically Inspired Cognitive Architectures 2019. BICA 2019. Advances in Intelligent Systems and Computing, vol 948. Springer, Cham. https://doi.org/10.1007/978-3-030-25719-4_45
Download citation
DOI: https://doi.org/10.1007/978-3-030-25719-4_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-25718-7
Online ISBN: 978-3-030-25719-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)