보조 분류기를 이용한 GAN 모델에서의데이터 증강 누출 방지 기법
A Scheme for Preventing Data Augmentation Leaks in GAN-based Models Using Auxiliary Classifier
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
데이터 증강이란 다양한 데이터 변환 및 왜곡을 통해 데이터셋의 크기와 품질을 개선하는 기법으로, 기계학습 모델의 과적합 문제를 해결하기 위한 대표적인 접근법이다. 그러나 심층학습 이미지 생성 모델인 GAN 기반 모델에서 데이터 증강을 적용하면 생성된이미지에 데이터 변환과 왜곡이 반영되는 증강 누출 문제가 발생하여 생성 이미지의 품질이 하락한다. 이러한 문제를 해결하기 위해본 논문에서는 데이터 증강의 종류와 수에 관계없이 증강 누출을 방지하는 기법을 제안한다. 증강 누출의 발생 조건을 분석하였으며, 보조적인 데이터 증강 작업 분류기를 GAN 모델에 적용하여 증강 누출을 방지하였다. 정성적 정량적 평가를 통해 제안된 기법을적용하면 증강 누출이 발생하지 않음을 보이고 추가적으로 생성 이미지의 품질을 향상시키며 기존 기법과 비교하여 발전된 성능을보임을 입증하였다.
Abstract
Data augmentation is general approach to solve overfitting of machine learning models by applying various datatransformations and distortions to dataset. However, when data augmentation is applied in GAN-based model,which is deep learning image generation model, data transformation and distortion are reflected in the generatedimage, then the generated image quality decrease. To prevent this problem called augmentation leak, we proposea scheme that can prevent augmentation leak regardless of the type and number of augmentations. Specifically, weanalyze the conditions of augmentation leak occurrence by type and implement auxiliary augmentation taskclassifier that can prevent augmentation leak. Through experiments, we show that the proposed techniqueprevents augmentation leak in the GAN model, and as a result improves the quality of the generated image. Wealso demonstrate the superiority of the proposed scheme through ablation study and comparison with otherrepresentative augmentation leak prevention technique.
참고문헌 (34)
- L. Perez, "The effectiveness of data augmentation in image classification using deep learning", arXiv preprint, ~ (2017)
- Connor Shorten, "A survey on Image Data Augmentation for Deep Learning", Journal of Big Data, 6(1), pp.1~48 (2019), Springer Science and Business Media LLC[DOI]
- F. Quiroga, "Revisiting data augmentation for rotational invariance in convolutional neural networks", International Conference on Modelling and Simulation in Management Sciences 2018, pp.127~141 (2018)
- I. Goodfellow, "Generative adversarial nets", Advances in neural information processing systems (2014)
- Ngoc-Trung Tran, "On Data Augmentation for GAN Training", IEEE Transactions on Image Processing, 30, pp.1882~1897 (2021), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- T. Karras, "Training generative adversarial networks with limited data. Advances in Neural Information Processing Systems", Advances in Neural Information Processing Systems, pp.12104~12114 (2020)[DOI]
- Z. Zhao, "Image augmentations for GAN training", arXiv preprint, ~ (2020)
- H. Zhang, "Consistency regularization for generative adversarial networks", International Conference of Leaning Representations (2020)
- Z. Zhao, "Improved consistency regularization for GANs", AAAI Conference on Artificial Intelligence (2021)
- A. Radford, "Unsupervised representation learning with deep convolutional generative adversarial networks", arXiv preprint, ~ (2015)
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Advances in neural information processing systems (2012)
- M. Arjovsky, "Wasserstein generative adversarial networks", International conference on machine learning, pp.214~223 (2017)
- Gulrajani, "Improved training of wasserstein GANs", Advances in neural information processing systems (2017)
- X. Mao, "Least squares generative adversarial networks", Proceedings of the IEEE international conference on computer vision, pp.2794~2802 (2017)
- T. Karras, "Progressive growing of GANs for improved quality, stability, and variation", arXiv preprint, ~ (2017)
- T. Karras, "A style-based generator architecture for generative adversarial networks", Proceedings of the IEEE, 2019, 4401~4410
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- Z. Cai, "Generative adversarial networks:A survey toward private and secure applications", ACM Computing Surveys, 54(6), pp.1~38 (2021)[DOI]
- Z. Lin, "PacGAN : The power of two samples in generative adversarial networks", Advances in neural information processing systems (2018)[DOI]
- L. Metz, "Unrolled generative adversarial networks", arXiv preprint, ~ (2016)
- Y. Yazici, "Empirical analysis of overfitting and mode drop in GAN training", IEEE International Conference on Image Processing, pp.1651~1655 (2020)
- H. Thanh-Tung, "Improving generalization and stability of generative adversarial networks", arXiv preprint, ~ (2019)
- S. Loffe, "Batch normalization:Accelerating deep network training by reducing internal covariate shift", International conference on machine learning, pp.448~456 (2015)
- B. Zhou, "Learning deep features for discriminative localization", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2921~2929 (2016)
- U. Ruby, "Binary cross entropy with deep learning technique for Image classification", International Journal of Advanced Trends in Computer Science and Engineering, 9(4), pp.5393~5397 (2020), The World Academy of Research in Science and Engineering[DOI]
- S. Yang, "From facial parts responses to face detection: A deep learning approach", Proceedings of the IEEE international conference on computer vision, pp.3676~3684 (2015)
- T. Miyato, "Spectral normalization for generative adversarial networks", arXiv preprint, ~ (2018)
- A. Radford, "Unsupervised representation learning with deep convolutional generative adversarial networks", arXiv preprint, ~ (2015)
- 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)
- D. P. Kingma, "Adam: A method for stochastic optimization", arXiv preprint, ~ (2014)
- M. Heusel, "Gans trained by a two time-scale update rule converge to a local nash equilibrium", Advances in neural information processing systems (2017)
- C. Szegedy, "Rethinking the inception architecture for computer vision", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2818~2826 (2016)
- T. Salimans, "Improved techniques for training GANs", Advances in neural information processing systems (2016)[DOI]
- A. Kolesnikov, "Revisiting self-supervised visual representation learning", Proceedings of the IEEE, 2019, 1920~1929