Wavelet Flow: Fast Training of High Resolution Normalizing Flows
- URL: http://arxiv.org/abs/2010.13821v1
- Date: Mon, 26 Oct 2020 18:13:43 GMT
- Title: Wavelet Flow: Fast Training of High Resolution Normalizing Flows
- Authors: Jason J. Yu, Konstantinos G. Derpanis, Marcus A. Brubaker
- Abstract summary: This paper introduces Wavelet Flow, a multi-scale, normalizing flow architecture based on wavelets.
A major advantage of Wavelet Flow is the ability to construct generative models for high resolution data that are impractical with previous models.
- Score: 27.661467862732792
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Normalizing flows are a class of probabilistic generative models which allow
for both fast density computation and efficient sampling and are effective at
modelling complex distributions like images. A drawback among current methods
is their significant training cost, sometimes requiring months of GPU training
time to achieve state-of-the-art results. This paper introduces Wavelet Flow, a
multi-scale, normalizing flow architecture based on wavelets. A Wavelet Flow
has an explicit representation of signal scale that inherently includes models
of lower resolution signals and conditional generation of higher resolution
signals, i.e., super resolution. A major advantage of Wavelet Flow is the
ability to construct generative models for high resolution data (e.g., 1024 x
1024 images) that are impractical with previous models. Furthermore, Wavelet
Flow is competitive with previous normalizing flows in terms of bits per
dimension on standard (low resolution) benchmarks while being up to 15x faster
to train.
Related papers
- Fast constrained sampling in pre-trained diffusion models [77.21486516041391]
Diffusion models have dominated the field of large, generative image models.
We propose an algorithm for fast-constrained sampling in large pre-trained diffusion models.
arXiv Detail & Related papers (2024-10-24T14:52:38Z) - Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow [65.51671121528858]
Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs.
Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path.
We propose Rectified Diffusion, which generalizes the design space and application scope of rectification to encompass the broader category of diffusion models.
arXiv Detail & Related papers (2024-10-09T17:43:38Z) - FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner [70.90505084288057]
Flow-based models tend to produce a straighter sampling trajectory during the sampling process.
We introduce several techniques including a pseudo corrector and sample-aware compilation to further reduce inference time.
FlowTurbo reaches an FID of 2.12 on ImageNet with 100 (ms / img) and FID of 3.93 with 38 (ms / img)
arXiv Detail & Related papers (2024-09-26T17:59:51Z) - Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization [37.35829410807451]
This paper introduces PeriodWave-Turbo, a high-fidelity and high-efficient waveform generation model via adversarial flow matching optimization.
It only requires 1,000 steps of fine-tuning to achieve state-of-the-art performance across various objective metrics.
By scaling up the backbone of PeriodWave from 29M to 70M parameters for improved generalization, PeriodWave-Turbo achieves unprecedented performance.
arXiv Detail & Related papers (2024-08-15T08:34:00Z) - PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator [73.80050807279461]
Piecewise Rectified Flow (PeRFlow) is a flow-based method for accelerating diffusion models.
PeRFlow achieves superior performance in a few-step generation.
arXiv Detail & Related papers (2024-05-13T07:10:53Z) - Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech.
Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
arXiv Detail & Related papers (2023-11-22T15:07:59Z) - Learning Non-linear Wavelet Transformation via Normalizing Flow [0.0]
An invertible transformation can be learned by a designed normalizing flow model.
With a factor-out scheme resembling the wavelet downsampling mechanism, one can train normalizing flow models to factor-out variables corresponding to fast patterns.
An analysis of the learned model in terms of low-pass/high-pass filters is given.
arXiv Detail & Related papers (2021-01-27T10:28:51Z) - WaveNODE: A Continuous Normalizing Flow for Speech Synthesis [15.051929807285847]
We propose a novel generative model called WaveNODE which exploits a continuous normalizing flow for speech synthesis.
WaveNODE places no constraint on the function used for flow operation, thus allowing the usage of more flexible and complex functions.
We experimentally show that WaveNODE achieves comparable performance with fewer parameters compared to the conventional flow-based vocoders.
arXiv Detail & Related papers (2020-06-08T13:49:36Z) - Normalizing Flows with Multi-Scale Autoregressive Priors [131.895570212956]
We introduce channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR)
Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data.
We show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
arXiv Detail & Related papers (2020-04-08T09:07:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.