FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

• URL: http://arxiv.org/abs/2312.03517v2
• Date: Tue, 2 Apr 2024 08:40:54 GMT
• Title: FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models
• Authors: Junhyuk So, Jungwon Lee, Eunhyeok Park,
• Abstract summary: We introduce an advanced acceleration technique that leverages the temporal redundancy inherent in diffusion models. Reusing feature maps with high temporal similarity opens up a new opportunity to save computation resources without compromising output quality.
• Score: 16.940023904740585
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The substantial computational costs of diffusion models, especially due to the repeated denoising steps necessary for high-quality image generation, present a major obstacle to their widespread adoption. While several studies have attempted to address this issue by reducing the number of score function evaluations (NFE) using advanced ODE solvers without fine-tuning, the decreased number of denoising iterations misses the opportunity to update fine details, resulting in noticeable quality degradation. In our work, we introduce an advanced acceleration technique that leverages the temporal redundancy inherent in diffusion models. Reusing feature maps with high temporal similarity opens up a new opportunity to save computation resources without compromising output quality. To realize the practical benefits of this intuition, we conduct an extensive analysis and propose a novel method, FRDiff. FRDiff is designed to harness the advantages of both reduced NFE and feature reuse, achieving a Pareto frontier that balances fidelity and latency trade-offs in various generative tasks.

Related papers

• Temporal Feature Matters: A Framework for Diffusion Model Quantization [105.3033493564844]
  Diffusion models rely on the time-step for the multi-round denoising. We introduce a novel quantization framework that includes three strategies. This framework preserves most of the temporal information and ensures high-quality end-to-end generation.
  arXiv  Detail & Related papers  (2024-07-28T17:46:15Z)
• Fast Unsupervised Tensor Restoration via Low-rank Deconvolution [0.09208007322096533]
  Low-rank Deconvolution (LRD) has appeared as a new multi-dimensional representation model that enjoys important efficiency and flexibility properties. We ask ourselves if this analytical model can compete against Deep Learning (DL) frameworks like Deep Image Prior (DIP) or Blind-Spot Networks (BSN)
  arXiv  Detail & Related papers  (2024-06-15T16:04:49Z)
• Spatial Annealing Smoothing for Efficient Few-shot Neural Rendering [106.0057551634008]
  We introduce an accurate and efficient few-shot neural rendering method named Spatial Annealing smoothing regularized NeRF (SANeRF) By adding merely one line of code, SANeRF delivers superior rendering quality and much faster reconstruction speed compared to current few-shot NeRF methods.
  arXiv  Detail & Related papers  (2024-06-12T02:48:52Z)
• Efficient Diffusion Model for Image Restoration by Residual Shifting [63.02725947015132]
  This study proposes a novel and efficient diffusion model for image restoration. Our method avoids the need for post-acceleration during inference, thereby avoiding the associated performance deterioration. Our method achieves superior or comparable performance to current state-of-the-art methods on three classical IR tasks.
  arXiv  Detail & Related papers  (2024-03-12T05:06:07Z)
• Fixed Point Diffusion Models [13.035518953879539]
  Fixed Point Diffusion Model (FPDM) is a novel approach to image generation that integrates the concept of fixed point solving into the framework of diffusion-based generative modeling. Our approach embeds an implicit fixed point solving layer into the denoising network of a diffusion model, transforming the diffusion process into a sequence of closely-related fixed point problems. We conduct experiments with state-of-the-art models on ImageNet, FFHQ, CelebA-HQ, and LSUN-Church, demonstrating substantial improvements in performance and efficiency.
  arXiv  Detail & Related papers  (2024-01-16T18:55:54Z)
• VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations [25.88881764546414]
  VQ-NeRF is an efficient pipeline for enhancing implicit neural representations via vector quantization. We present an innovative multi-scale NeRF sampling scheme that concurrently optimize the NeRF model at both compressed and original scales. We incorporate a semantic loss function to improve the geometric fidelity and semantic coherence of our 3D reconstructions.
  arXiv  Detail & Related papers  (2023-10-23T01:41:38Z)
• Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
  Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
  arXiv  Detail & Related papers  (2023-06-01T03:08:28Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.