paper-with-me

Papers

Dynamically Masked Discriminator for GANs

2023-09-21 · NeurIPS 2023 11

Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However, the distribution of generated data changes throughout the training process, which is difficult for the discriminator to learn. In this paper, we propose a novel method for GANs from the viewpoint of online continual learning. We observe that the discriminator model, trained on historically generated data, often slows down its adaptation to the changes in the new arrival generated data, which accordingly decreases the quality of generated results. By treating the generated data in training as a stream, we propose to detect whether the discriminator slows down the learning of new knowledge in generated data. Therefore, we can explicitly enforce the discriminator to learn new knowledge fast. Particularly, we propose a new discriminator, which automatically detects its retardation and then dynamically masks its features, such that the discriminator can adaptively learn the temporally-vary distribution of generated data. Experimental results show our method outperforms the state-of-the-art approaches.

📄 PDF Abstract BibTeX

Code (1)

wentianzhang-ml/dmd 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Dynamically Masked Discriminator for Generative Adversarial Networks

2023-06-13 · Wentian Zhang, Haozhe Liu, Bing Li, Jinheng Xie 외

Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However, the distribution of generated data chang…

Continual Learning

Few-shot Image Generation via Masked Discrimination

2022-10-27 · Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan

Few-shot image generation aims to generate images of high quality and great diversity with limited data. However, it is difficult for modern GANs to avoid overfitting when trained on only a few images. The discriminator …

DiversityImage Generation

Improving the Training of Data-Efficient GANs via Quality Aware Dynamic Discriminator Rejection Sampling

2025-01-01 · CVPR 2025 1 · Zhaoyu Zhang, Yang Hua, Guanxiong Sun, Hui Wang 외

Data-Efficient Generative Adversarial Nets (DE-GANs) have become more and more popular in recent years. Existing methods apply data augmentation, noise injection and pre-trained models to maximumly increase the numbe…

Data Augmentation

Metric Learning-based Generative Adversarial Network

2017-11-08 · Zi-Yi Dou

Generative Adversarial Networks (GANs), as a framework for estimating generative models via an adversarial process, have attracted huge attention and have proven to be powerful in a variety of tasks. However, training GA…

Generative Adversarial NetworkMetric Learning

Bidirectional Conditional Generative Adversarial Networks

2017-11-20 · Ayush Jaiswal, Wael Abd-Almageed, Yue Wu, Premkumar Natarajan

Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples ($x$) conditioned on both latent variables ($z$) and known auxiliary information ($c$). We propose the Bidirectional…