Multi-view Adversarially Learned Inference for Cross-domain Joint Distribution Matching

By Changying Du, Changde Du, Xingyu Xie, Chen Zhang, Hao Wang. 2018

26 citations recorded by the source corpus.

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-to-image translation, image-to-attribute generation (multi-label classification), attribute-to-image 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, compared to those methods that compute similarities in the high-dimensional data space.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Divya Saxena
2. Jiannong Cao
3. Bolei Zhou
4. Ming-Hsuan Yang
5. Jing-Hao Xue
6. Yulun Zhang
7. Yujiu Yang
8. Weihao Xia

In Computer Vision and Pattern Recognition

1. Yujiu Yang
2. Ming-Hsuan Yang
3. Weihao Xia
4. Yulun Zhang
5. Jing-Hao Xue
6. Luc Van Gool
7. Bolei Zhou
8. Lei Zhang

In Representation & Self-Supervised Learning

1. Divya Saxena
2. Jiannong Cao
3. Bolei Zhou
4. Ming-Hsuan Yang
5. Jing-Hao Xue
6. Yulun Zhang
7. Yujiu Yang
8. Weihao Xia

Citations in the corpus

• GAN Inversion: A Survey (2021, background): “Similar to GAN inversion, Adversarial Feature Learning (AFL, also known as BiGAN) [111], [175], [176] or Adversarially Learned Inference (ALI) [112], [177], [178] also aims to learn the inverse mapping of GAN models1.”
• Generative Adversarial Networks (GANs) (2020, background): “In recent times, several researchers have explored both unsupervised [7], [198]–[207] and semi-supervised image-to-image translation [208]–[210].”