Timezone: »

 
Poster
Mining GOLD Samples for Conditional GANs
Sangwoo Mo · Chiheon Kim · Sungwoong Kim · Minsu Cho · Jinwoo Shin

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #83
in Deep Learning -- Generative Models »

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 efficiently, 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.

Keywords: Adversarial Networks · Generative Models · Deep Learning
[ Paper]  [ Poster] 

Author Information

Sangwoo Mo (KAIST)
Chiheon Kim (Kakao Brain)
Sungwoong Kim (Kakao Brain)
Minsu Cho (POSTECH)
Jinwoo Shin (KAIST; AITRICS)

More from the Same Authors