Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation

2020-09-11 · ICCV 2019 10 · Jinghua Wang, Jianmin Jiang

Machine learning models trained in one domain perform poorly in the other domains due to the existence of domain shift. Domain adaptation techniques solve this problem by training transferable models from the label-rich source domain to the label-scarce target domain. Unfortunately, a majority of the existing domain adaptation techniques rely on the availability of target-domain data, and thus limit their applications to a small community across few computer vision problems. In this paper, we tackle the challenging zero-shot domain adaptation (ZSDA) problem, where target-domain data is non-available in the training stage. For this purpose, we propose conditional coupled generative adversarial networks (CoCoGAN) by extending the coupled generative adversarial networks (CoGAN) into a conditioning model. Compared with the existing state of the arts, our proposed CoCoGAN is able to capture the joint distribution of dual-domain samples in two different tasks, i.e. the relevant task (RT) and an irrelevant task (IRT). We train CoCoGAN with both source-domain samples in RT and dual-domain samples in IRT to complete the domain adaptation. While the former provide high-level concepts of the non-available target-domain data, the latter carry the sharing correlation between the two domains in RT and IRT. To train CoCoGAN in the absence of target-domain data for RT, we propose a new supervisory signal, i.e. the alignment between representations across tasks. Extensive experiments carried out demonstrate that our proposed CoCoGAN outperforms existing state of the arts in image classifications.

📄 PDF Abstract BibTeX arXiv:2009.05228

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization

2022-10-26 · Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

We propose a novel method for training a conditional generative adversarial network (CGAN) without the use of training data, called zero-shot learning of a CGAN (ZS-CGAN). Zero-shot learning of a conditional generator on…

Data Free Quantization Generative Adversarial Network Quantization Zero-Shot Learning

Conditional MoCoGAN for Zero-Shot Video Generation

2021-09-13 · Shun Kimura, Kazuhiko Kawamoto

We propose a conditional generative adversarial network (GAN) model for zero-shot video generation. In this study, we have explored zero-shot conditional generation setting. In other words, we generate unseen videos from…

Generative Adversarial Network Image Generation Video Generation

Transductive Zero-Shot Learning by Decoupled Feature Generation

2021-02-05 · Federico Marmoreo, Jacopo Cavazza, Vittorio Murino

In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. We focus on the transductive setting, in which unlabelled visual d…

Zero-Shot Learning

Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning

2020-12-30 · Tasfia Shermin, Shyh Wei Teng, Ferdous Sohel, Manzur Murshed 외

Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen domains and…

Generalized Zero-Shot Learning Generative Adversarial Network Zero-Shot Learning

CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language

2019-09-21 · Zhi Chen, Jingjing Li, Yadan Luo, Zi Huang 외

Existing methods using generative adversarial approaches for Zero-Shot Learning (ZSL) aim to generate realistic visual features from class semantics by a single generative network, which is highly under-constrained. As a…

Generative Adversarial Network Zero-Shot Learning