paper-with-me

홈 › Papers

MisGAN: Learning from Incomplete Data with Generative Adversarial Networks

2019-02-25 · ICLR 2019 5 · Steven Cheng-Xian Li, Bo Jiang, Benjamin Marlin

Generative adversarial networks (GANs) have been shown to provide an effective way to model complex distributions and have obtained impressive results on various challenging tasks. However, typical GANs require fully-observed data during training. In this paper, we present a GAN-based framework for learning from complex, high-dimensional incomplete data. The proposed framework learns a complete data generator along with a mask generator that models the missing data distribution. We further demonstrate how to impute missing data by equipping our framework with an adversarially trained imputer. We evaluate the proposed framework using a series of experiments with several types of missing data processes under the missing completely at random assumption.

📄 PDF Abstract BibTeX arXiv:1902.09599

Code (1)

steveli/misgan 공식 구현 pytorch

Tasks

Abstract Argumentation

Similar Papers 제목 키워드 기반

End-to-End Rubbing Restoration Using Generative Adversarial Networks

2022-05-08 · Gongbo Sun, Zijie Zheng, Ming Zhang

Rubbing restorations are significant for preserving world cultural history. In this paper, we propose the RubbingGAN model for restoring incomplete rubbing characters. Specifically, we collect characters from the Zhang M…

Generative Adversarial Network

Differentiable and Scalable Generative Adversarial Models for Data Imputation

2022-01-10 · Yangyang Wu, Jun Wang, Xiaoye Miao, Wenjia Wang 외

Data imputation has been extensively explored to solve the missing data problem. The dramatically increasing volume of incomplete data makes the imputation models computationally infeasible in many real-life applications…

Imputation

Overcoming Missing and Incomplete Modalities with Generative Adversarial Networks for Building Footprint Segmentation

2018-08-09 · Benjamin Bischke, Patrick Helber, Florian König, Damian Borth 외

The integration of information acquired with different modalities, spatial resolution and spectral bands has shown to improve predictive accuracies. Data fusion is therefore one of the key challenges in remote sensing. M…

Semantic Segmentation

Generative Multi-View Human Action Recognition

2019-10-01 · ICCV 2019 10 · Lichen Wang, Zhengming Ding, Zhiqiang Tao, Yunyu Liu 외

Multi-view action recognition targets to integrate complementary information from different views to improve classification performance. It is a challenging task due to the distinct gap between heterogeneous feature doma…

Action RecognitionTemporal Action Localization

An Efficient Deep Learning Approach Using Improved Generative Adversarial Networks for Incomplete Information Completion of Self-driving

2021-09-01 · Jingzhi Tu, Gang Mei, Francesco Piccialli

Autonomous driving is the key technology of intelligent logistics in Industrial Internet of Things (IIoT). In autonomous driving, the appearance of incomplete point clouds losing geometric and semantic information is ine…

Autonomous DrivingCollision AvoidanceGenerative Adversarial Networkobject-detection+2