Abstract
This paper proposes an efficient domain adaption approach using deep learning along with transfer and meta-level learning. The objective is to identify how many blocks (i.e. groups of consecutive layers) of a pre-trained image classification network need to be fine-tuned based on the characteristics of the new task. In order to investigate it, a number of experiments have been conducted using different pre-trained networks and image datasets. The networks were fine-tuned, starting from the blocks containing the output layers and progressively moving towards the input layer, on various tasks with characteristics different from the original task. The amount of fine-tuning of a pre-trained network (i.e. the number of top layers requiring adaptation) is usually dependent on the complexity, size, and domain similarity of the original and new tasks. Considering these characteristics, a question arises of how many blocks of the network need to be fine-tuned to get maximum possible accuracy? Which of a number of available pre-trained networks require fine-tuning of the minimum number of blocks to achieve this accuracy? The experiments, that involve three network architectures each divided into 10 blocks on average and five datasets, empirically confirm the intuition that there exists a relationship between the similarity of the original and new tasks and the depth of network needed to fine-tune in order to achieve accuracy comparable with that of a model trained from scratch. Further analysis shows that the fine-tuning of the final top blocks of the network, which represent the high-level features, is sufficient in most of the cases. Moreover, we have empirically verified that less similar tasks require fine-tuning of deeper portions of the network, which however is still better than training a network from scratch.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ali, A., Gabrys, B., Budka, M.: Cross-domain meta-learning for time-series forecasting. Proc. Comput. Sci. 126, 9–18 (2018)
Alom, Z., Taha, T.M., Yakopcic, C., Westberg, S., et al.: The history began from AlexNet: a comprehensive survey on deep learning approaches. Computing Research Repository (CoRR) arxiv:abs/1803.01164 (2018)
Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. Computing Research Repository (CoRR) arxiv:abs/1611.02167 (2016)
Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 – mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446–461. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_29
Demner-Fushman, D., Kohli, M.D., Rosenman, M.B., Shooshan, S.E., et al.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23(2), 304–310 (2016)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106(1), 59–70 (2007)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1126–1135. PMLR, International Convention Centre, Sydney, August 2017
Hassannejad, H., Matrella, G., Ciampolini, P., De Munari, I., Mordonini, M., Cagnoni, S.: Food image recognition using very deep convolutional networks. In: Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management, MADiMa 2016, pp. 41–49. ACM, New York (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Hem, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. Computing Research Repository (CoRR) arxiv:abs/1406.4729 (2014)
Hinton, G., Srivastava, N., Swersky, K.: Overview of mini-batch gradient descent lecture of neural networks for machine learning course (2014). http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf
Lemke, C., Budka, M., Gabrys, B.: Metalearning: a survey of trends and technologies. Artif. Intell. Rev. 44, 117–130 (2015)
Lin, K., Yang, H.F., Chen, C.S.: Flower classification with few training examples via recalling visual patterns from deep CNN, pp. 41–49. CVGIP (2015)
Lin, T., Maire, M., Belongie, S.J., Bourdev, L.D., et al.: Microsoft COCO: common objects in context. Computing Research Repository (CoRR) arxiv:abs/1405.0312 (2014)
Mallya, A., Lazebnik, S.: Piggyback: adding multiple tasks to a single, fixed network by learning to mask. Computing Research Repository (CoRR) arxiv:abs/1801.06519 (2018)
Miikkulainen, R., Liang, J.Z., Meyerson, E., Rawal, A., et al.: Evolving deep neural networks. Computing Research Repository (CoRR) arxiv:abs/1703.00548 (2017)
Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics Image Processing, pp. 722–729 (2008)
Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., et al.: ChexNet: radiologist-level pneumonia detection on chest x-rays with deep learning. Computing Research Repository (CoRR) arxiv:abs/1711.05225 (2017)
Russakovsky, O., Deng, J., Su, H., Krause, J., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Shin, H., Roberts, K., Lu, L., Demner-Fushman, D., Yao, J., Summers, R.M.: Learning to read chest x-rays: recurrent neural cascade model for automated image annotation. Computing Research Repository (CoRR) arxiv:abs/1603.08486 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computing Research Repository (CoRR) arxiv:abs/1409.1556 (2014)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 4–9 February 2017, San Francisco, California, USA, pp. 4278–4284 (2017)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR) (2015). http://arxiv.org/abs/1409.4842
Szegedy, C., Vanhoucke, V., Ioffe, S., et al.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 June 2016, pp. 2818–2826 (2016)
Vilalta, R., Drissi, Y.: A perspective view and survey of meta-learning. Artif. Intell. Rev. 18(2), 77–95 (2002)
Wang, D., Zheng, T.F.: Transfer learning for speech and language processing. In: 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1225–1237 (2015)
Wang, X., Peng, Y., Lu, L., Lu, Z., et al.: ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Computing Research Repository (CoRR) arxiv:abs/1705.02315 (2017)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Proceedings of the 27th International Conference on Neural Information Processing Systems, NIPS 2014, vol. 2, pp. 3320–3328. MIT Press, Cambridge (2014)
Zhang, Z., Sun, Z., Liu, J., Chen, J., et al.: An experimental comparison of deep neural networks for end-to-end speech recognition. Computing Research Repository (CoRR) arxiv:abs/1611.07174 (2016)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. Computing Research Repository (CoRR) arxiv:abs/1611.01578 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ali, A.R., Budka, M., Gabrys, B. (2019). Towards Meta-learning of Deep Architectures for Efficient Domain Adaptation. In: Nayak, A., Sharma, A. (eds) PRICAI 2019: Trends in Artificial Intelligence. PRICAI 2019. Lecture Notes in Computer Science(), vol 11671. Springer, Cham. https://doi.org/10.1007/978-3-030-29911-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-29911-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29910-1
Online ISBN: 978-3-030-29911-8
eBook Packages: Computer ScienceComputer Science (R0)