GAN

이론/GAN

[논문리뷰] CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

2024.04.18

소개 https://arxiv.org/abs/2005.09544 CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks The unprecedented increase in the usage of computer vision technology in society goes hand in hand with an increased concern in data privacy. In many real-world scenarios like people tracking or action recognition, it is important to be able to process the arxiv.org 저는 스테이블 디퓨전을 사용한 비식별..

이론/GAN

[GAN] DCGAN

2022.06.06

DCGAN(Deep Convolutional GAN)은 GAN의 대표적인 모델로써, GAN에 컨볼루전망을 적용하여 성능을 향상시킨 모델입니다. 간단하게 DCGAN에 대해 설명한 후 실습과 함께 상세하게 알아보도록 하겠습니다. DCGAN 요약 DCGAN은 2016년에 발표된 모델로 GAN의 가장 대표적인 모델입니다. https://arxiv.org/abs/1511.06434 Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption ..

[논문리뷰] CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

[GAN] DCGAN

티스토리툴바