MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis

By Animesh Karnewar, Oliver Wang, Raghu Sesha Iyengar. 2019

50 citations recorded by the source corpus.

While Generative Adversarial Networks (GANs) have seen huge successes in image synthesis tasks, they are notoriously difficult to use, in part due to instability during training. One commonly accepted reason for this instability is that gradients passing from the discriminator to the generator can quickly become uninformative, due to a learning imbalance during training. In this work, we propose the Multi-Scale Gradient Generative Adversarial Network (MSG-GAN), a simple but effective technique for addressing this problem which allows the flow of gradients from the discriminator to the generator at multiple scales. This technique provides a stable approach for generating synchronized multi-scale images. We present a very intuitive implementation of the mathematical MSG-GAN framework which uses the concatenation operation in the discriminator computations. We empirically validate the effect of our MSG-GAN approach through experiments on the CIFAR10 and Oxford102 flowers datasets and compare it with other relevant techniques which perform multi-scale image synthesis. In addition, we also provide details of our experiment on CelebA-HQ dataset for synthesizing 1024 x 1024 high resolution images.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Generative Models

Citations in the corpus

Analyzing and Improving the Image Quality of StyleGAN (2019, methodology): “Figure 7a shows MSG-GAN [19], which connects the matching resolutions of the generator and discriminator using multiple skip connections.”
Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis (2021, methodology): “A deeper model with more convolution layers leads to a longer training time of GAN, due to the increased number of model parameters and a weaker gradient ﬂow through G (Zhang et al., 2017; Karras et al., 2017; Karnewar & Wang, 2019).”
Wavelet Flow: Fast Training of High Resolution Normalizing Flows (2020, background): “Various subsequent works [47, 21, 43, 20, 48, 41] also follow a stage-wise multi-scale image generation approach but forego the residual modelling and directly generate higher resolution images given lower resolutions inputs.”
Image Inpainting with Learnable Feature Imputation (2020, methodology): “tainty-weighted average and U-Net skip connections with our revised skip connection (see Equation 6). Furthermore, we replace progressive growing training [21] with Multi-Scale Gradient GAN (MSG-GAN) [19]. For the MSG-GAN, instead of matching different resolutions from the generator with the discrim”