Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
Flow models have recently made great progress at modeling ordinal discrete data such as images and audio. Due to the continuous nature of flow models, dequantization is typically applied when using them for such discrete data, resulting in lower bound estimates of the likelihood. In this paper, we introduce subset flows, a class of flows that can tractably transform finite volumes and thus allow exact computation of likelihoods for discrete data. Based on subset flows, we identify ordinal discrete autoregressive models, including WaveNets, PixelCNNs and Transformers, as single-layer flows. We use the flow formulation to compare models trained and evaluated with either the exact likelihood or its dequantization lower bound. Finally, we study multilayer flows composed of PixelCNNs and non-autoregressive coupling layers and demonstrate state-of-the-art results on CIFAR-10 for flow models trained with dequantization.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Conditional Image Generation with PixelCNN Decoders
This work explores conditional image generation with a new image density model based on the PixelCNN architecture. The model can be conditioned on any vector, including descriptive labels or tags, or latent embeddings cr…
Conditional Image GenerationDecoderDensity EstimationDescriptive+1Audio Dequantization for High Fidelity Audio Generation in Flow-based Neural Vocoder
In recent works, a flow-based neural vocoder has shown significant improvement in real-time speech generation task. The sequence of invertible flow operations allows the model to convert samples from simple distribution …
Audio DequantizationAudio GenerationImage GenerationFlow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have much worse density modeling performance co…
Computational EfficiencyDensity EstimationImage GenerationMulti-Scale Architectures Matter: On the Adversarial Robustness of Flow-based Lossless Compression
As a probabilistic modeling technique, the flow-based model has demonstrated remarkable potential in the field of lossless compression \cite{idf,idf++,lbb,ivpf,iflow},. Compared with other deep generative models (eg. Aut…
Adversarial RobustnessDensity EstimationPixelVAE: A Latent Variable Model for Natural Images
Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and model global structure well but have difficulty capturing small details. P…
Decodermodel