Multi-scale Generative Modeling for Fast Sampling

• URL: http://arxiv.org/abs/2411.09356v1
• Date: Thu, 14 Nov 2024 11:01:45 GMT
• Title: Multi-scale Generative Modeling for Fast Sampling
• Authors: Xiongye Xiao, Shixuan Li, Luzhe Huang, Gengshuo Liu, Trung-Kien Nguyen, Yi Huang, Di Chang, Mykel J. Kochenderfer, Paul Bogdan,
• Abstract summary: In the wavelet domain, we encounter unique challenges, especially the sparse representation of high-frequency coefficients. We propose a multi-scale generative modeling in the wavelet domain that employs distinct strategies for handling low and high-frequency bands. As supported by the theoretical analysis and experimental results, our model significantly improve performance and reduce the number of trainable parameters, sampling steps, and time.
• Score: 38.570968785490514
• License:
• Abstract: While working within the spatial domain can pose problems associated with ill-conditioned scores caused by power-law decay, recent advances in diffusion-based generative models have shown that transitioning to the wavelet domain offers a promising alternative. However, within the wavelet domain, we encounter unique challenges, especially the sparse representation of high-frequency coefficients, which deviates significantly from the Gaussian assumptions in the diffusion process. To this end, we propose a multi-scale generative modeling in the wavelet domain that employs distinct strategies for handling low and high-frequency bands. In the wavelet domain, we apply score-based generative modeling with well-conditioned scores for low-frequency bands, while utilizing a multi-scale generative adversarial learning for high-frequency bands. As supported by the theoretical analysis and experimental results, our model significantly improve performance and reduce the number of trainable parameters, sampling steps, and time.

Related papers

• FreSh: Frequency Shifting for Accelerated Neural Representation Learning [11.175745750843484]
  Implicit Neural Representations (INRs) have recently gained attention as a powerful approach for continuously representing signals such as images, videos, and 3D shapes using multilayer perceptrons (MLPs) Low-frequency details are known to exhibit a low-frequency bias, limiting their ability to capture high-frequency details accurately. We propose frequency shifting (or FreSh) to align the frequency spectrum of the initial output with that of the target signal.
  arXiv  Detail & Related papers  (2024-10-07T14:05:57Z)
• PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation [37.35829410807451]
  We propose PeriodWave, a novel universal waveform generation model. We introduce a period-aware flow matching estimator that can capture the periodic features of the waveform signal. We also propose a single period-conditional universal estimator that can feed-forward parallel by period-wise batch inference.
  arXiv  Detail & Related papers  (2024-08-14T13:36:17Z)
• Score-based Generative Models with Adaptive Momentum [40.84399531998246]
  We propose an adaptive momentum sampling method to accelerate the transforming process. We show that our method can produce more faithful images/graphs in small sampling steps with 2 to 5 times speed up.
  arXiv  Detail & Related papers  (2024-05-22T15:20:27Z)
• Boosting Diffusion Models with Moving Average Sampling in Frequency Domain [101.43824674873508]
  Diffusion models rely on the current sample to denoise the next one, possibly resulting in denoising instability. In this paper, we reinterpret the iterative denoising process as model optimization and leverage a moving average mechanism to ensemble all the prior samples. We name the complete approach "Moving Average Sampling in Frequency domain (MASF)"
  arXiv  Detail & Related papers  (2024-03-26T16:57:55Z)
• Blue noise for diffusion models [50.99852321110366]
  We introduce a novel and general class of diffusion models taking correlated noise within and across images into account. Our framework allows introducing correlation across images within a single mini-batch to improve gradient flow. We perform both qualitative and quantitative evaluations on a variety of datasets using our method.
  arXiv  Detail & Related papers  (2024-02-07T14:59:25Z)
• DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models [58.450152413700586]
  We introduce a soft absorbing state that facilitates the diffusion model in learning to reconstruct discrete mutations based on the underlying Gaussian space. We employ state-of-the-art ODE solvers within the continuous space to expedite the sampling process. Our proposed method effectively accelerates the training convergence by 4x and generates samples of similar quality 800x faster.
  arXiv  Detail & Related papers  (2023-10-09T15:29:10Z)
• Stage-by-stage Wavelet Optimization Refinement Diffusion Model for Sparse-View CT Reconstruction [14.037398189132468]
  We present an innovative approach named the Stage-by-stage Wavelet Optimization Refinement Diffusion (SWORD) model for sparse-view CT reconstruction. Specifically, we establish a unified mathematical model integrating low-frequency and high-frequency generative models, achieving the solution with optimization procedure. Our method rooted in established optimization theory, comprising three distinct stages, including low-frequency generation, high-frequency refinement and domain transform.
  arXiv  Detail & Related papers  (2023-08-30T10:48:53Z)
• WaveDM: Wavelet-Based Diffusion Models for Image Restoration [43.254438752311714]
  Wavelet-Based Diffusion Model (WaveDM) learns the distribution of clean images in the wavelet domain conditioned on the wavelet spectrum of degraded images after wavelet transform. WaveDM achieves state-of-the-art performance with the efficiency that is comparable to traditional one-pass methods.
  arXiv  Detail & Related papers  (2023-05-23T08:41:04Z)
• Q-Diffusion: Quantizing Diffusion Models [52.978047249670276]
  Post-training quantization (PTQ) is considered a go-to compression method for other tasks. We propose a novel PTQ method specifically tailored towards the unique multi-timestep pipeline and model architecture. We show that our proposed method is able to quantize full-precision unconditional diffusion models into 4-bit while maintaining comparable performance.
  arXiv  Detail & Related papers  (2023-02-08T19:38:59Z)
• Real Time Speech Enhancement in the Waveform Domain [99.02180506016721]
  We present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is capable of removing various kinds of background noise including stationary and non-stationary noises.
  arXiv  Detail & Related papers  (2020-06-23T09:19:13Z)

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.