Abstract
The training process of GAN can be regarded as a process in which the generation network and the identification network play against each other and finally reach a state where it cannot be further improved if the opponent does not change. At the same time, the start of the gradient descent method will choose a direction to reduce the defined loss. The loss function plays a key role in the performance of the model. Choosing the right loss function can help your model learn how to focus on the correct set of features in the data to achieve optimal and faster convergence. In this work, we propose a novel loss function scheme, namely, Diminish Smooth L1 loss. We improve a robust L1 loss called Smooth L1 loss by lowering the threshold so that the network can converge to a lower minimum. From our experimental results on several benchmark data, we found that our algorithm often outperforms the previous approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gatys, L.A., Ecker, A.S., Bethge, M.: Image Style Transfer Using Convolutional Neural Networks (2016)
Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss Functions for Image Restoration with Neural Networks, 28 November 2015
Zhang, L., Zhang, L., Mou, X., Zhang, D.: A Comprehensive Evaluation of Full Reference Image Quality Assessment Algorithms (2012)
Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X.: Dynamic R-CNN: towards high quality object detection via dynamic training. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 260–275. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_16
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)
Wang, W., Liu, J., Yang, S., Guo, Z.: Typography With Decor: Intelligent Text Style Transfer (2019)
Tyleček, R., Šára, R.: Spatial pattern templates for recognition of objects with regular structure, pp. 364–374 (2013)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, 18 May 2015
Mirza, M., Osindero, S.: Conditional Generative Adversarial Nets, 6 November 2014
Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-Image Translation with Conditional Adversarial Networks, 21 November 2016
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems (NIPS 2017), vol. 30, 26 June 2017
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved Training of Wasserstein GANs, 31 March 2017
Goodfellow, I.J., et al.: Generative Adversarial Networks, 10 June 2014
Girshick, R.: Fast R-CNN, 30 April 2015
Fu, C.-Y., Shvets, M., Berg, A.C.: RetinaMask: Learning to Predict Masks Improves State-of-the-Art Single-Shot Detection for Free, 10 January 2019
Kukacka, J., Golkov, V., Cremers, D.: Regularization for Deep Learning: A Taxonomy, CoRR, vol. abs/1710.10686 (2017)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN, CoRR, vol. abs/1701.07875 (2017)
Pathak, D., Krähenbühl, P., Donahue, J., Darrell, T., Efros, A.A.: Context Encoders: Feature Learning by Inpainting. CoRR, vol. abs/1604.07379 (2016)
Acknowledgment
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2018R1D1A1A02050166) and Institute for Information and Communications Technology Promotion (IITP), South Korea grant funded by the Korea Government (MSIT) (No. 2018–0-00245, Development of prevention technology against AI dysfunction induced by deception attack).
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
Sutanto, A.R., Kang, DK. (2021). A Novel Diminish Smooth L1 Loss Model with Generative Adversarial Network. In: Singh, M., Kang, DK., Lee, JH., Tiwary, U.S., Singh, D., Chung, WY. (eds) Intelligent Human Computer Interaction. IHCI 2020. Lecture Notes in Computer Science(), vol 12615. Springer, Cham. https://doi.org/10.1007/978-3-030-68449-5_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-68449-5_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68448-8
Online ISBN: 978-3-030-68449-5
eBook Packages: Computer ScienceComputer Science (R0)