Visible to the public Metric-Based Generative Adversarial Network

TitleMetric-Based Generative Adversarial Network
Publication TypeConference Paper
Year of Publication2017
AuthorsDai, Guoxian, Xie, Jin, Fang, Yi
Conference NameProceedings of the 25th ACM International Conference on Multimedia
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-4906-2
Keywordsdata-dependent margin, deep metric learning, Generative Adversarial Learning, generative adversarial network, Metrics, pubcrawl, resilience, Resiliency, Scalability

Existing methods of generative adversarial network (GAN) use different criteria to distinguish between real and fake samples, such as probability [9],energy [44] energy or other losses [30]. In this paper, by employing the merits of deep metric learning, we propose a novel metric-based generative adversarial network (MBGAN), which uses the distance-criteria to distinguish between real and fake samples. Specifically, the discriminator of MBGAN adopts a triplet structure and learns a deep nonlinear transformation, which maps input samples into a new feature space. In the transformed space, the distance between real samples is minimized, while the distance between real sample and fake sample is maximized. Similar to the adversarial procedure of existing GANs, a generator is trained to produce synthesized examples, which are close to real examples, while a discriminator is trained to maximize the distance between real and fake samples to a large margin. Meanwhile, instead of using a fixed margin, we adopt a data-dependent margin [30], so that the generator could focus on improving the synthesized samples with poor quality, instead of wasting energy on well-produce samples. Our proposed method is verified on various benchmarks, such as CIFAR-10, SVHN and CelebA, and generates high-quality samples.

Citation Keydai_metric-based_2017