Freedom: Training-free energy-guided conditional diffusion model
Recently, conditional diffusion models have gained popularity in numerous applications due
to their exceptional generation ability. However, many existing methods are training …
to their exceptional generation ability. However, many existing methods are training …
Learning visual prior via generative pre-training
Various stuff and things in visual data possess specific traits, which can be learned by deep
neural networks and are implicitly represented as the visual prior, eg, object location and …
neural networks and are implicitly represented as the visual prior, eg, object location and …
Adaptivemix: Improving gan training via feature space shrinkage
Due to the outstanding capability for data generation, Generative Adversarial Networks
(GANs) have attracted considerable attention in unsupervised learning. However, training …
(GANs) have attracted considerable attention in unsupervised learning. However, training …
DivGAN: A diversity enforcing generative adversarial network for mode collapse reduction
Abstract Generative Adversarial Networks (GANs) are one of the most efficient generative
models to generate data. They have made breakthroughs in many computer vision tasks …
models to generate data. They have made breakthroughs in many computer vision tasks …
SAC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic
Learning expressive stochastic policies instead of deterministic ones has been proposed to
achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy …
achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy …
Dynamically masked discriminator for GANs
Abstract Training Generative Adversarial Networks (GANs) remains a challenging problem.
The discriminator trains the generator by learning the distribution of real/generated data …
The discriminator trains the generator by learning the distribution of real/generated data …
Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks
Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative
modeling conditional on continuous scalar variables (termed regression labels). However …
modeling conditional on continuous scalar variables (termed regression labels). However …
Detection of AI-Generated Synthetic Images with a Lightweight CNN
The rapid development of generative adversarial networks has significantly advanced the
generation of synthetic images, presenting valuable opportunities and ethical dilemmas in …
generation of synthetic images, presenting valuable opportunities and ethical dilemmas in …
Advcloak: Customized adversarial cloak for privacy protection
With extensive face images being shared on social media, there has been a notable
escalation in privacy concerns. In this paper, we propose AdvCloak, an innovative …
escalation in privacy concerns. In this paper, we propose AdvCloak, an innovative …
Improving GAN training via feature space shrinkage
Due to the outstanding capability for data generation, Generative Adversarial Networks
(GANs) have attracted considerable attention in unsupervised learning. However, training …
(GANs) have attracted considerable attention in unsupervised learning. However, training …