UU-Nets Connecting Discriminator and Generator for Image to Image Translation
Adversarial generative model have successfully manifest itself in image synthesis. However, the performance deteriorate and unstable, because discriminator is far stable than generator, and it is hard to control the game between the two modules. Various methods have been introduced to tackle the problem such as WGAN, Relativistic GAN and their successors by adding or restricting the loss function, which certainly help balance the min-max game, but they all focused on the loss function ignoring the intrinsic structure limitation. We present a UU-Net architecture inspired by U-net bridging the encoder and the decoder, UU-Net composed by two U-Net liked modules respectively served as generator and discriminator. Because the modules in U-net are symmetrical, therefore it shares weights easily between all four components. Thanks to UU-net's modules identical and symmetric property, we could not only carried the features from inner generator's encoder to its decoder, but also to the discriminator's encoder and decoder. By this design, it give us more control and condition flexibility to intervene the process between the generator and the discriminator.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderImage GenerationImage-to-Image TranslationTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Triple Generative Adversarial Nets
Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL). However, existing GANs in SSL have two problems: (1) the generator and the discriminator (i.e. the classifier)…
Image GenerationConditional Generative Adversarial Network for Structured Domain Adaptation
In recent years, deep neural nets have triumphed over many computer vision problems, including semantic segmentation, which is a critical task in emerging autonomous driving and medical image diagnostics applications. In…
Autonomous DrivingDomain AdaptationGenerative Adversarial NetworkSemantic SegmentationDual Discriminator Generative Adversarial Nets
We propose in this paper a novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be very effective, especially in addressing some k…
Generative Adversarial NetworkMGAN: Training Generative Adversarial Nets with Multiple Generators
We propose in this paper a new approach to train the Generative Adversarial Nets (GANs) with a mixture of generators to overcome the mode collapsing problem. The main intuition is to employ multiple generators, instead o…
Crossing Nets: Combining GANs and VAEs with a Shared Latent Space for Hand Pose Estimation
State-of-the-art methods for 3D hand pose estimation from depth images require large amounts of annotated training data. We propose to model the statistical relationships of 3D hand poses and corresponding depth images u…
3D Hand Pose EstimationCPUHand Pose EstimationPose Estimation