.png){kind=icon}
返回
Zero-Shot Learning Based on Quality-Verifying Adversarial Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2021.3119854.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, generative adversarial network (GAN)based zero-shot learning methods have attracted widespread attention. However, due to the randomness of GAN generation, mast existing methods cannot well guarantee to generate sufficiently reliable features and have good generalization ability. Targeting at these problems, we propose an effective Quality-Verifying Adversarial Network (QVAN) that consists of one generator and double discriminators. Adversarial learning between the former discriminator and generator is to generate visual features, which can be partitioned into pseudo-generated features and reliable-generated features. The latter discriminator is used for quality-verifying that will guide the generator to generate more reliable features that are near the real visual features. To avoid over-fitting and ensure intra-class diversity, we set the threshold for each class to distinguish pseudo-generated features and reliable-generated features. To further preserve both compactness and discrim inability of the samples, we introduce the class metric constraint, which are more conducive to classification. Moreover, we introduce l(1,2)-norm constraint to fully consider the specific distribution among different classes, thus making the generated features more discriminant. Extensive experiments on several real-world datasets show the effectiveness of the proposed approach, which demonstrate the advantage over the state-of-the-art methods.
Keyword:
Zero-shot learning
generative adversarial network
quality-verifying
class metric constraint
l(12)-norm constraint
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
查看更多内容