물체 변형 성능을 향상하기 위한 U-net 및 Residual 기반의Cycle-GAN
U-net and Residual-based Cycle-GAN for Improving Object Transfiguration Performance
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
The image-to-image translation is one of the deep learning applications using image data. In this paper, we aim at improving the performance of object transfiguration which transforms a specific object in an image into another specific object. For object transfiguration, it is required to transform only the target object and maintain background images. In the existing results, however, it is observed that other parts in the image are also transformed. In this paper, we have focused on the structure of artificial neural networks that are frequently used in the existing methods and have improved the performance by adding constraints to the exiting structure. We also propose the advanced structure that combines the existing structures to maintain their advantages and complement their drawbacks. The effectiveness of the proposed methods are shown in experimental results.
Abstract
The image-to-image translation is one of the deep learning applications using image data. In this paper, we aim at improving the performance of object transfiguration which transforms a specific object in an image into another specific object. For object transfiguration, it is required to transform only the target object and maintain background images. In the existing results, however, it is observed that other parts in the image are also transformed. In this paper, we have focused on the structure of artificial neural networks that are frequently used in the existing methods and have improved the performance by adding constraints to the exiting structure. We also propose the advanced structure that combines the existing structures to maintain their advantages and complement their drawbacks. The effectiveness of the proposed methods are shown in experimental results.
참고문헌 (16)
- P. Isola, "Image-to-image translation with conditional adversarial networks", 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.5967~5976 (2017)
- R. Zhang, "Colorful image colorization", European Conference on Computer Vision, pp.649~666 (2016)
- [URL]
- I. Goodfellow, "Generative adversarial nets", 28th Annual Conference on Neural Information Processing Systems, pp.2672~2680 (2014)
- J.-Y. Zhu, "Unpaired image-to-image translation using cycle-consistent adversarial networks", 2017 IEEE International Conference on Computer Vision, pp.2242~2251 (2017)
- O. Russakovsky, "ImageNet Large scale visual recognition challenge", International Journal of Computer Vision, 115(3), pp.211~252 (2015)[DOI]
- T. Kim, "Learning to discover cross-domain relations with generative adversarial networks", International Conference on Machine Learning, pp.1857~1865 (2017)
- Z. Yi, "Dualgan: Unsupervised dual learning for image-to-image translation", IEEE International Conference on Computer Vision, pp.2868~2876 (2017)
- K. He, "Deep residual learning for image recognition", 2017 IEEE International Conference on Computer Vision, pp.770~778 (2016)
- K. He, "Identity mappings in deep residual networks", European Conference on Computer Vision, pp.630~645 (2016)
- J. Johnson, "Perceptual losses for real-time style transfer and super-resolution", European Conference on Computer Vision, pp.694~711 (2016)
- O. Ronneberger, "U-net: Convolutional networks for biomedical image segmentation", International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.234~241 (2015)
- X. Mao, "Least squares generative adversarial networks", 2017 IEEE International Conference on Computer Vision, pp.2813~2821 (2017)
- A. Shrivastava, "Learning from simulated and unsupervised images through adversarial training", 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.2242~2251 (2017)
- E. Borenstein, "Combined top-down", bottom-up segmentation, 2008, pp.30(12), 2109~2125
- W. Mokrzycki, "Color difference ΔE - A survey", Machine Graphic and Vision, 20(4), pp.383~411 (2011)