전체 글301 [2025-1] 박서형 - StyleGAN : A Style-Based Generator Architecture for Generative Adversarial Networks https://arxiv.org/abs/1812.04948 A Style-Based Generator Architecture for Generative Adversarial NetworksWe propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identitarxiv.org 0. Abstract 본 논문은 style tr.. 2025. 5. 3. [2025-1] 김유현 - Least Squares Generative Adversarial Networks https://arxiv.org/abs/1611.04076 Least Squares Generative Adversarial NetworksUnsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to tarxiv.org 0. Abstract기존 GAN은 Discriminator에서 sigmoid cross-entro.. 2025. 5. 3. [2025-1] 최민서 - Maximum Likelihood Training of Score-Based Diffusion Models [논문링크] https://arxiv.org/abs/2101.09258 Maximum Likelihood Training of Score-Based Diffusion ModelsScore-based diffusion models synthesize samples by reversing a stochastic process that diffuses data to noise, and are trained by minimizing a weighted combination of score matching losses. The log-likelihood of score-based diffusion models can be tractablarxiv.org [Score-based diffusion models 논문리.. 2025. 5. 2. [2025-1] 전윤경-CLEAR: Comprehensive Learning EnabledAdversarial Reconstruction for Subtle StructureEnhanced Low-Dose CT Imaging CLEAR( Comprehensive Learning Enabled Adversarial Reconstruction) : 저선량 CT 이미징에서 고품질 이미지를 재구성하기 위한 심층 학습 기반의 방법포괄적 도메인(프로젝션, 이미지) 에서 구축된 생성자다중 수준의 손실WGAN-GP 기반 모달리티( Wasserstein 거리 기반의 적대적 최적화 )Method노이즈 모델포아송 노이즈 모델Z_i:광자의 수Z_0i: 입사한 X-선 광자 강도P_i: 감쇠 계수의 선적분E_i: 배경 전자 노이즈I_RD: 일상선량 이미지I_LD: 재구성된 저선량 이미지I_N: 노이즈 이미지,R: 재구성 연산P_LD: 저선량 프로젝션P_N: 프로젝션의 노이즈,P_RD:일상선량 프로젝션 CLEAR: 일괄 재구성 방법최적의 생성기 g*.. 2025. 5. 2. 이전 1 ··· 4 5 6 7 8 9 10 ··· 76 다음
