The week's pick
Reseach Article
Image to Image Translation using Deep Learning Techniques
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 175 - Number 22 |
| Year of Publication: 2020 |
| Authors: S. Ramya, S. Anchana, A.M. Bavidhraa Shrrei, R. Devanand |
10.5120/ijca2020920745
|
S. Ramya, S. Anchana, A.M. Bavidhraa Shrrei, R. Devanand . Image to Image Translation using Deep Learning Techniques. International Journal of Computer Applications. 175, 22 ( Oct 2020), 40-42. DOI=10.5120/ijca2020920745
Abstract
This project aims to make image-to-image translation for different tasks using deep learning techniques. Using dataset generated by a combination of online images. We have generated images for different tasks. Our innovation is we train and test the cycle-consistent adversarial networks using dataset. We have tried to fine-tune hyper parameters such as batch size, learning rate, lambda in loss function and trying to add dropout to our network. The experiment outcomes show that our method can successfully transfer for disparate tasks while conserving the original content.
References
- L. Gatys, A. Ecker, and M. Bethge. A neural algorithm of artistic style.arXivpreprint arXiv.•1508.06576, 2015.
- J. Zhu, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision, 2017.
- I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio- Generative adversarial nets. In NIPS, 2014.
- Z. Kalal, K. Mikolajczyk, and J. Matas. Forward- backward error: Automatic detection of tracking failures. In ICPR, 2010.
- J. Long, E. Shelhamer, and T. Darrell, ‘‘Fully convolutional networks for semantic segmentation,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Aug. 2015, pp. 3431–3440.
- P. Isola, J. Y. Zhu, T. Zhou, and A. Efros, ‘‘Image- to-image translation with conditional adversarial networks,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Aug. 2017, pp. 1125–1134.
- T. Kim, M. Cha, H. Kim, J. K. Lee, and J. Kim. (2017). ‘‘Learning to discover cross-domain relations with generative adversarial networks.’’ [Online].Available:https://arxiv.org/abs/1703.05192
- Z. Yi, R. Hao, P. Tan, and M. Gong, ‘‘DualGAN: Unsupervised dual learning for image-to-image translation,’’ in Proc. ICCV, Aug. 2017, pp. 2868– 2876.
- j. Y. Zhu, T. Park, P. Isola, and A. A. Efros. (2017). ‘‘Unpaired image-toimage translation using cycle- consistent adversarial networks.’’ [Online]. Available: https://arxiv.org/abs/1703.10593.
- M. Y. Liu, T. Breuel, and J. Kautz, ‘‘Unsupervised image-to-image translation networks,’’ in Proc.Adv. Neural Inf. Process. Syst., 2017, pp. 700–708
- X. Huang, M. Y. Liu, S. Belongie, and J. Kautz. (2018). ‘‘Multimodal unsupervised image-to-image translation.’’[Online].Available:https://arxiv.org/abs/1804.04732.
- Y. Choi, M. Choi, and M. Kim, ‘‘Stargan: Unified generative adversarial networks for multi-domain image-to-image translation,’’ Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jul. 2018, pp. 3662–3670.
- H. Y. Lee, H. Y. Tseng, J. B. Huang, M. Singh, and M. H. Yang, ‘‘Diverse image-to-image translation via disentangled representations,’’ in Proc. ECCV, Sep. 2018, pp. 35–51.
- N. Liu, J. Han, and M. H. Yang, ‘‘PiCANet: Learning pixel-wise contextual attention for saliency detection,’’ Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Aug. 2018, pp. 3089–3098.
Index Terms
Keywords