Mining GOLD Samples for Conditional GANs

10/21/2019
by   Sangwoo Mo, et al.
9

Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex generation tasks. We introduce a simple yet effective approach to improving cGANs by measuring the discrepancy between the data distribution and the model distribution on given samples. The proposed measure, coined the gap of log-densities (GOLD), provides an effective self-diagnosis for cGANs while being efficienty computed from the discriminator. We propose three applications of the GOLD: example re-weighting, rejection sampling, and active learning, which improve the training, inference, and data selection of cGANs, respectively. Our experimental results demonstrate that the proposed methods outperform corresponding baselines for all three applications on different image datasets.

READ FULL TEXT
research
02/24/2021

Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks

Despite remarkable performance in producing realistic samples, Generativ...
research
02/03/2023

Leveraging Contaminated Datasets to Learn Clean-Data Distribution with Purified Generative Adversarial Networks

Generative adversarial networks (GANs) are known for their strong abilit...
research
02/02/2018

No Modes left behind: Capturing the data distribution effectively using GANs

Generative adversarial networks (GANs) while being very versatile in rea...
research
02/11/2020

Task-Aware Variational Adversarial Active Learning

Deep learning has achieved remarkable performance in various tasks thank...
research
10/23/2018

Reproducing AmbientGAN: Generative models from lossy measurements

In recent years, Generative Adversarial Networks (GANs) have shown subst...
research
10/17/2018

Adversarial Balancing for Causal Inference

Biases in observational data pose a major challenge to estimation method...
research
07/25/2021

MuSe-Toolbox: The Multimodal Sentiment Analysis Continuous Annotation Fusion and Discrete Class Transformation Toolbox

We introduce the MuSe-Toolbox - a Python-based open-source toolkit for c...

Please sign up or login with your details

Forgot password? Click here to reset