Work

Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons

Year: 2020

Type: conference-paper

Abstract: Conditional generative adversarial networks have shown exceptional generation performance over the past few years. However, they require large numbers of annotations. To address this problem, we propose a novel generative adversarial network utilizing weak supervision in the form of pairwise comparisons (PC-GAN) for image attribute editing. In the light of Bayesian uncertainty estimation and noise-tolerant adversarial training, PC-GAN can estimate attribute rating efficiently and demonstrate robust performance in noise resistance. Through extensive experiments, we show both qualitatively and quantitatively that PC-GAN performs comparably with fully-supervised methods and outperforms unsupervised baselines. Code and Supplementary can be found on the project website*.

Source: Proceedings of the AAAI Conference on Artificial Intelligence

DOI: 10.1609/aaai.v34i07.6723

Authors: Ligong Han, Ruijiang Gao, Mun Kim, Xin Tao, Bo Liu, Dimitris Metaxas

Institutions: Rutgers, The State University of New Jersey, The University of Texas at Austin, Tencent (China)

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funder: National Science Foundation

Awards: CHS: Medium: Data Driven Biomechanically Accurate Modeling of Human Gait on Unconstrained Terrain, AitF: Collaborative Research: Topological Algorithms for 3D/4D Cardiac Images: Understanding Complex and Dynamic Structures, Phase 1 IUCRC Rutgers-New Brunswick: Center for Accelerated Real Time Analytics (CARTA), CHS: Medium: Collaborative Research: Scalable Integration of Data-Driven and Model-Based Methods for Large Vocabulary Sign Recognition and Search