Timezone: »
In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128 × 128 resolution image samples exhibiting global coherence. We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models. These analyses demonstrate that high resolution samples provide class information not present in low resolution samples. Across 1000 ImageNet classes, 128 × 128 samples are more than twice as discriminable as artificially resized 32×32 samples. In addition, 84.7% of the classes have samples exhibiting diversity comparable to real ImageNet data.
Summary/Notes]
Author Information
Augustus Odena (Google Brain)
Christopher Olah (Google Brain)
I want to understand things clearly and explain them well. Research scientist on [Google Brain](http://g.co/brain), co-editor of [Distill](http://distill.pub).
Jon Shlens (Google Brain)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Talk: Conditional Image Synthesis with Auxiliary Classifier GANs »
Mon. Aug 7th 04:06 -- 04:24 AM Room Parkside 1
More from the Same Authors
-
2020 Poster: Small-GAN: Speeding up GAN Training using Core-Sets »
Samrath Sinha · Han Zhang · Anirudh Goyal · Yoshua Bengio · Hugo Larochelle · Augustus Odena -
2020 Poster: Revisiting Spatial Invariance with Low-Rank Local Connectivity »
Gamaleldin Elsayed · Prajit Ramachandran · Jon Shlens · Simon Kornblith -
2019 Poster: TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing »
Augustus Odena · Catherine Olsson · David Andersen · Ian Goodfellow -
2019 Oral: TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing »
Augustus Odena · Catherine Olsson · David Andersen · Ian Goodfellow -
2019 Poster: Self-Attention Generative Adversarial Networks »
Han Zhang · Ian Goodfellow · Dimitris Metaxas · Augustus Odena -
2019 Oral: Self-Attention Generative Adversarial Networks »
Han Zhang · Ian Goodfellow · Dimitris Metaxas · Augustus Odena -
2018 Poster: Is Generator Conditioning Causally Related to GAN Performance? »
Augustus Odena · Jacob Buckman · Catherine Olsson · Tom B Brown · Christopher Olah · Colin Raffel · Ian Goodfellow -
2018 Oral: Is Generator Conditioning Causally Related to GAN Performance? »
Augustus Odena · Jacob Buckman · Catherine Olsson · Tom B Brown · Christopher Olah · Colin Raffel · Ian Goodfellow