MSaGAN: 얼굴 속성 편집을 위한 유도 마스크와 다중작업 학습 접근을 사용한 개선된 SaGAN
MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 얼굴 속성 편집(facial attribute editing)의 연구는 GAN(Generative Adversarial Net)과 인코더- 디코더(encoder-decoder) 구조를 활용하여 사실적인 결과를 얻고 있다. 최신 연구 중 하나인SaGAN(Spatial attention GAN)은 공간적 주의 기제(spatial attention mechanism)를 활용하여 얼굴 영상에서 원하는 속성만을 변경할 방법을 제안하였다. 그러나 불충분한 얼굴 영역 정보로 인하여때로 부자연스러운 결과를 얻는 경우가 발생한다. 본 논문에서는 기존 연구의 한계점을 개선하기위하여 유도 마스크(guide mask)를 학습에 활용하고, 다중작업 학습(multitask learning) 접근을 적용한 개선된 SaGAN(MSaGAN)을 제안한다. 폭넓은 실험을 통해 마스크 손실 함수와 신경망 구조에따른 얼굴 속성 편집의 결과를 비교하여 제안하는 방법이 기존보다 더 자연스러운 결과를 효율적으로 얻을 수 있음을 보인다.
Abstract
Recently, studies of facial attribute editing have obtained realistic results using generative adversarial net (GAN) and encoder-decoder structure. Spatial attention GAN (SaGAN), one of the latest researches, is the method that can change only desired attribute in a face image by spatial attention mechanism. However, sometimes unnatural results are obtained due to insufficient information on face areas. In this paper, we propose an improved SaGAN (MSaGAN) using a guide mask for learning and applying multitask learning approach to improve the limitations of the existing methods. Through extensive experiments, we evaluated the results of the facial attribute editing in therms of the mask loss function and the neural network structure. It has been shown that the proposed method can efficiently produce more natural results compared to the previous methods.
참고문헌 (18)
- Xin Zheng, "A Survey of Deep Facial Attribute Analysis", International Journal of Computer Vision, 128(8-9), pp.2002~2034 (2020), Springer Science and Business Media LLC[DOI]
- 최태준, "얼굴 2D 이미지의 3D 모델 변환 알고리즘", 한국컴퓨터정보학회논문지, 20(4), pp.41~48 (2015), 한국컴퓨터정보학회
- 배석찬, "비전기반 얼굴인식 인증 및 등록지원 병원정보시스템", 한국컴퓨터정보학회논문지, 24(12), pp.59~65 (2019), 한국컴퓨터정보학회[DOI]
- I. J. Goodfellow, "Generative Adversarial Nets", Advances in neural information processing systems, pp.2672~2680 (2014)
- W. Shen, "Learning Residual Images for Face Attribute Manipulation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.4030~4038 (2017)
- H. S. Yang, "Study on Performance Improvement of SAGAN using Mask", Proceeding of 2019 Korea Signal Processing Conference, pp.2557~2560 (2019)
- G. Zhang, "Generative Adversarial Network with Spatial Attention for Face Attribute Editing", Proceedings of the European Conference on Computer Vision (ECCV), pp.417~432 (2018)
- Zhenliang He, "AttGAN: Facial Attribute Editing by Only Changing What You Want", IEEE Transactions on Image Processing, 28(11), pp.5464~5478 (2019), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- H. S. Yang, "Face Attribute Editing using AttGAN and Guide Mask", 2019 International Conference on Electronics, Information, and Communication (ICEIC), pp.1~3 (2019)
- 우상근, "딥러닝 네트워크를 이용한 조영증강 CT 영상 생성", 한국컴퓨터정보학회논문지, 24(3), pp.41~47 (2019), 한국컴퓨터정보학회[DOI]
- A. Radford, "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks", arXiv preprint arXiv : 1511. 06434v2, 1~16 (2016)
- M. Mirza, "Conditional Generative Adversarial Nets", arXiv preprint arXiv:1411.1784, 1~7 (2014)
- G. Perarnau, "Invertible Conditional GANs for Image Editing", NIPS 2016Workshop on Adversarial Training, pp.1~9 (2016)
- P. Isola, "Image-to-Image Translation with Conditional Adversarial Networks", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1125~1134 (2017)
- J. Y. Zhu, "Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks", Proceedings of the IEEE international conference on computer vision, pp.2223~2232 (2017)
- Y. Choi, "StarGAN : Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.8789~8797 (2018)
- Z. Liu, "Deep Learning Face Attributes in the Wild", Proceedings of the IEEE International Conference on Computer Vision, pp.3730~3738 (2015)
- C. H. Lee, "MaskGAN : Towards Diverse and Interactive Facial Image Manipulation", arXiv preprint arXiv : 1907. 11922v2, 1~20 (2020)