CVDec 30, 2021

A Novel Generator with Auxiliary Branch for Improving GAN Performance

arXiv:2112.14968v210 citations
Originality Incremental advance
AI Analysis

This work addresses a specific bottleneck in GAN training for image generation, offering incremental improvements in model performance.

The paper tackles the problem of information flow impediment in GAN generators by introducing a novel architecture with main and auxiliary branches and a gated feature fusion module, resulting in improved performance, such as boosting FID from 35.13 to 25.00 and IS from 20.23 to 25.57 on tiny-ImageNet.

The generator in the generative adversarial network (GAN) learns image generation in a coarse-to-fine manner in which earlier layers learn the overall structure of the image and the latter ones refine the details. To propagate the coarse information well, recent works usually build their generators by stacking up multiple residual blocks. Although the residual block can produce a high-quality image as well as be trained stably, it often impedes the information flow in the network. To alleviate this problem, this brief introduces a novel generator architecture that produces the image by combining features obtained through two different branches: the main and auxiliary branches. The goal of the main branch is to produce the image by passing through the multiple residual blocks, whereas the auxiliary branch is to convey the coarse information in the earlier layer to the later one. To combine the features in the main and auxiliary branches successfully, we also propose a gated feature fusion module that controls the information flow in those branches. To prove the superiority of the proposed method, this brief provides extensive experiments using various standard datasets including CIFAR-10, CIFAR-100, LSUN, CelebA-HQ, AFHQ, and tiny-ImageNet. Furthermore, we conducted various ablation studies to demonstrate the generalization ability of the proposed method. Quantitative evaluations prove that the proposed method exhibits impressive GAN performance in terms of Inception score (IS) and Frechet inception distance (FID). For instance, the proposed method boosts the FID and IS scores on the tiny-ImageNet dataset from 35.13 to 25.00 and 20.23 to 25.57, respectively.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes