Timezone: »

 
Oral
Emerging Convolutions for Generative Normalizing Flows
Emiel Hoogeboom · Rianne Van den Berg · Max Welling

Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Hall A
in Deep Generative Models »

Generative flows are attractive because they admit exact likelihood optimization and efficient image synthesis. Recently, Kingma & Dhariwal (2018) demonstrated with Glow that generative flows are capable of generating high quality images. We generalize the 1 × 1 convolutions proposed in Glow to invertible d × d convolutions, which are more flexible since they operate on both channel and spatial axes. We propose two methods to produce invertible convolutions, that have receptive fields identical to standard convolutions: Emerging convolutions are obtained by chaining specific autoregressive convolutions, and periodic convolutions are decoupled in the frequency domain. Our experiments show that the flexibility of d × d convolutions significantly improves the performance of generative flow models on galaxy images, CIFAR10 and ImageNet.

[ Slides] 

Author Information

Emiel Hoogeboom (University of Amsterdam)
Rianne Van den Berg (University of Amsterdam)
Max Welling (University of Amsterdam & Qualcomm)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors