Abstract
The current standard for a variety of computer vision tasks using smaller numbers of labelled training examples is to fine-tune from weights pre-trained on a large image classification dataset such as ImageNet. The application of transfer learning and transfer learning methods tends to be rigidly binary. A model is either pre-trained or not pre-trained. Pre-training a model either increases performance or decreases it, the latter being defined as negative transfer. Application of L2-SP regularisation that decays the weights towards their pre-trained values is either applied or all weights are decayed towards 0. This paper re-examines these assumptions. Our recommendations are based on extensive empirical evaluation that demonstrate the application of a non-binary approach to achieve optimal results. (1) Achieving best performance on each individual dataset requires careful adjustment of various transfer learning hyperparameters not usually considered, including number of layers to transfer, different learning rates for different layers and different combinations of L2SP and L2 regularization. (2) Best practice can be achieved using a number of measures of how well the pre-trained weights fit the target dataset to guide optimal hyperparameters. We present methods for non-binary transfer learning including combining L2SP and L2 regularization and performing non-traditional fine-tuning hyperparameter searches. Finally we suggest heuristics for determining the optimal transfer learning hyperparameters. The benefits of using a non-binary approach are supported by final results that come close to or exceed state of the art performance on a variety of tasks that have traditionally been more difficult for transfer learning.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Agrawal, P., Girshick, R., Malik, J.: Analyzing the performance of multilayer neural networks for object recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 329–344. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10584-0_22
Azizpour, H., Razavian, A.S., Sullivan, J., Maki, A., Carlsson, S.: Factors of transferability for a generic convnet representation. IEEE Trans. Pattern Anal. Mach. Intell. 38(9), 1790–1802 (2015)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR (2020)
Chu, B., Madhavan, V., Beijbom, O., Hoffman, J., Darrell, T.: Best practices for fine-tuning visual classifiers to new domains. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 435–442. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_34
Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3606–3613 (2014)
Cui, Y., Song, Y., Sun, C., Howard, A., Belongie, S.: Large scale fine-grained categorization and domain-specific transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4109–4118 (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009 (2009)
Fukenaga, K.: Introduction to Statistical Pattern Recognition, 2nd edn. Academic Press, San Diego (1990)
Griffin, G., Holub, A., Perona, P.: Caltech256 object category dataset. California Institute of Technology (2007)
Guo, Y., Shi, H., Kumar, A., Grauman, K., Rosing, T., Feris, R.: SpotTune: transfer learning through adaptive fine-tuning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4805–4814 (2019)
He, K., Girshick, R., Dollár, P.: Rethinking ImageNet pre-training. arXiv preprint arXiv:1811.08883 (2018)
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)
Kolesnikov, A., et al.: Big transfer (bit): general visual representation learning. arXiv preprint arXiv:1912.11370 (2019)
Kornblith, S., Shlens, J., Le, Q.V.: Do better ImageNet models transfer better? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2661–2671 (2019)
Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR 2013), Sydney, Australia (2013)
Li, H., et al.: Rethinking the hyperparameters for fine-tuning. arXiv preprint arXiv:2002.11770 (2020)
Li, S., Deng, W.: Deep facial expression recognition: a survey. IEEE Trans. Affect. Comput. (2020)
Li, X., Xiong, H., Wang, H., Rao, Y., Liu, L., Huan, J.: Delta: deep learning transfer using feature map with attention for convolutional networks. arXiv preprint arXiv:1901.09229 (2019)
Li, X., Grandvalet, Y., Davoine, F.: Explicit inductive bias for transfer learning with convolutional networks. arXiv preprint arXiv:1802.01483 (2018)
Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 185–201. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_12
Maji, S., Kannala, J., Rahtu, E., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. Technical report, Toyota Technological Institute at Chicago (2013)
Masi, I., Wu, Y., Hassner, T., Natarajan, P.: Deep face recognition: a survey. In: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 471–478. IEEE (2018)
Ng, H.W., Nguyen, V.D., Vonikakis, V., Winkler, S.: Deep learning for emotion recognition on small datasets using transfer learning. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 443–449 (2015)
Ngiam, J., Peng, D., Vasudevan, V., Kornblith, S., Le, Q.V., Pang, R.: Domain adaptive transfer learning with specialist models. arXiv preprint arXiv:1811.07056 (2018)
Plested, J., Gedeon, T.: An analysis of the interaction between transfer learning protocols in deep neural networks. In: Gedeon, T., Wong, K.W., Lee, M. (eds.) ICONIP 2019. LNCS, vol. 11953, pp. 312–323. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-36708-4_26
Ridnik, T., Lawen, H., Noy, A., Friedman, I.: TResNet: high performance GPU-dedicated architecture. arXiv preprint arXiv:2003.13630 (2020)
Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. Int. J. Comput. Vision 40(2), 99–121 (2000)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resNet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Wan, R., Xiong, H., Li, X., Zhu, Z., Huan, J.: Towards making deep transfer learning never hurt. In: 2019 IEEE International Conference on Data Mining (ICDM), pp. 578–587. IEEE (2019)
Wightman, R.: PyTorch image models. https://github.com/rwightman/pytorch-image-models (2019). https://doi.org/10.5281/zenodo.4414861
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems, pp. 3320–3328 (2014)
Zhuang, P., Wang, Y., Qiao, Y.: Learning attentive pairwise interaction for fine-grained classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 13130–13137, No. 07 in 34 (2020)
Zoph, B., et al.: Rethinking pre-training and self-training. arXiv preprint arXiv:2006.06882 (2020)
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
Plested, J., Shen, X., Gedeon, T. (2021). Rethinking Binary Hyperparameters for Deep Transfer Learning. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13109. Springer, Cham. https://doi.org/10.1007/978-3-030-92270-2_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-92270-2_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92269-6
Online ISBN: 978-3-030-92270-2
eBook Packages: Computer ScienceComputer Science (R0)