Effective Shortcut Technique for GAN
This work addresses performance bottlenecks in GANs for image generation, offering a domain-specific improvement that is incremental in nature.
The paper tackles the problem of improving GAN-based image generation by proposing a gated shortcut method that enhances information propagation in residual blocks, resulting in improved Frechet inception distance (FID) and Inception score (IS) on datasets like tiny-ImageNet, e.g., FID from 35.13 to 27.90 and IS from 20.23 to 23.42.
In recent years, generative adversarial network (GAN)-based image generation techniques design their generators by stacking up multiple residual blocks. The residual block generally contains a shortcut, \ie skip connection, which effectively supports information propagation in the network. In this paper, we propose a novel shortcut method, called the gated shortcut, which not only embraces the strength point of the residual block but also further boosts the GAN performance. More specifically, based on the gating mechanism, the proposed method leads the residual block to keep (or remove) information that is relevant (or irrelevant) to the image being generated. To demonstrate that the proposed method brings significant improvements in the GAN performance, this paper provides extensive experimental results on the various standard datasets such as CIFAR-10, CIFAR-100, LSUN, and tiny-ImageNet. Quantitative evaluations show that the gated shortcut achieves the impressive GAN performance in terms of Frechet inception distance (FID) and Inception score (IS). For instance, the proposed method improves the FID and IS scores on the tiny-ImageNet dataset from 35.13 to 27.90 and 20.23 to 23.42, respectively.