Abstract | ||
---|---|---|
•We propose a residual generator (Rg-GAN) served as a better approximation divergence minimization framework for GAN, and prove that residual generator for standard and least-squares GAN are equivalent to the minimization of reverse-KL and a new instance of f-divergence, respectively.•We prove that Rg-GAN can be reduced to IPMs based GAN and bridge the gap between IPMs and f-divergence.•We propose a new loss function for the discriminator of Rg-GAN that manifests a better discriminative property and therefore improved on Rg-GAN generalisation ability.•We conduct experiments on multiple benchmark data sets and demonstrate that our proposed framework can mitigate the mode collapse issue and facilitate GAN to generate higher-quality images with negligible additional computation cost. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.patcog.2021.108222 | Pattern Recognition |
Keywords | DocType | Volume |
Generative adversarial networks,Image synthesis,Deep learning | Journal | 121 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aurele Tohokantche Gnanha | 1 | 0 | 0.34 |
Wen-Ming Cao | 2 | 26 | 11.53 |
Xudong Mao | 3 | 105 | 10.64 |
Si Wu | 4 | 148 | 16.73 |
Hau-San Wong | 5 | 1008 | 86.89 |
Qing Li | 6 | 3222 | 433.87 |