图 书 馆
跨域联合分布匹配的多视点对抗学习推理Multi-view Adversarially Learned Inference for Cross-domain Joint Distribution Matching |
|
| 课程网址: | http://videolectures.net/kdd2018_du_adversarially_cross-domain/ |
| 主讲教师: | Changyin Du |
| 开课单位: | 中国科学院计算技术研究所 |
| 开课时间: | 2018-11-23 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Many important data mining problems can be modeled as learning a (bidirectional) multidimensional mapping between two data domains. Based on the generative adversarial networks (GANs), particularly conditional ones, cross-domain joint distribution matching is an increasingly popular kind of methods addressing such problems. Though significant advances have been achieved, there are still two main disadvantages of existing models, i.e., the requirement of large amount of paired training samples and the notorious instability of training. In this paper, we propose a multi-view adversarially learned inference (ALI) model, termed as MALI, to address these issues. Unlike the common practice of learning direct domain mappings, our model relies on shared latent representations of both domains and can generate arbitrary number of paired faking samples, benefiting from which usually very few paired samples (together with sufficient unpaired ones) is enough for learning good mappings. Extending the vanilla ALI model, we design novel discriminators to judge the quality of generated samples (both paired and unpaired), and provide theoretical analysis of our new formulation. Experiments on image translation, image-to-attribute and attribute-toimage generation tasks demonstrate that our semi-supervised learning framework yields significant performance improvements over existing ones. Results on cross-modality retrieval show that our latent space based method can achieve competitive similarity search performance in relative fast speed, |
| 关 键 词: | 数据挖掘问题; 学习两个数据域; 大量配对训练样本; 连同足够的未配对样本 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-01-30：cyh |
| 最后编审: | 2023-01-31：cyh |
| 阅读次数: | 24 |