Temporal Feature Matters: A Framework for Diffusion Model Quantization
- URL: http://arxiv.org/abs/2407.19547v2
- Date: Wed, 7 Aug 2024 20:43:10 GMT
- Title: Temporal Feature Matters: A Framework for Diffusion Model Quantization
- Authors: Yushi Huang, Ruihao Gong, Xianglong Liu, Jing Liu, Yuhang Li, Jiwen Lu, Dacheng Tao,
- Abstract summary: 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.
- Score: 105.3033493564844
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The Diffusion models, widely used for image generation, face significant challenges related to their broad applicability due to prolonged inference times and high memory demands. Efficient Post-Training Quantization (PTQ) is crucial to address these issues. However, unlike traditional models, diffusion models critically rely on the time-step for the multi-round denoising. Typically, each time-step is encoded into a hypersensitive temporal feature by several modules. Despite this, existing PTQ methods do not optimize these modules individually. Instead, they employ unsuitable reconstruction objectives and complex calibration methods, leading to significant disturbances in the temporal feature and denoising trajectory, as well as reduced compression efficiency. To address these challenges, we introduce a novel quantization framework that includes three strategies: 1) TIB-based Maintenance: Based on our innovative Temporal Information Block (TIB) definition, Temporal Information-aware Reconstruction (TIAR) and Finite Set Calibration (FSC) are developed to efficiently align original temporal features. 2) Cache-based Maintenance: Instead of indirect and complex optimization for the related modules, pre-computing and caching quantized counterparts of temporal features are developed to minimize errors. 3) Disturbance-aware Selection: Employ temporal feature errors to guide a fine-grained selection between the two maintenance strategies for further disturbance reduction. This framework preserves most of the temporal information and ensures high-quality end-to-end generation. Extensive testing on various datasets, diffusion models and hardware confirms our superior performance and acceleration..
Related papers
- Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting [16.782154479264126]
Predicting backbone-temporal traffic flow presents challenges due to complex interactions between temporal factors.
Existing approaches address these dimensions in isolation, neglecting their critical interdependencies.
In this paper, we introduce Sanonymous-Temporal Unitized Unitized Cell (ASTUC), a unified framework designed to capture both spatial and temporal dependencies.
arXiv Detail & Related papers (2024-11-14T07:34:31Z) - HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration [18.170285241800798]
We propose a novel method that Harmonizes training and inference with a novel learning-based Caching framework.
Compared to the traditional training paradigm, the newly proposed SDT maintains the continuity of the denoising process.
IEPO integrates an efficient proxy mechanism to approximate the final image error caused by reusing the cached feature.
arXiv Detail & Related papers (2024-10-02T16:34:29Z) - TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models [40.5153344875351]
We introduce TMPQ-DM, which jointly optimize timestep reduction and quantization to achieve a superior performance-efficiency trade-off.
For timestep reduction, we devise a non-uniform grouping scheme tailored to the non-uniform nature of the denoising process.
In terms of quantization, we adopt a fine-grained layer-wise approach to allocate varying bit-widths to different layers based on their respective contributions to the final generative performance.
arXiv Detail & Related papers (2024-04-15T07:51:40Z) - QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning [52.157939524815866]
In this paper, we empirically unravel three properties in quantized diffusion models that compromise the efficacy of current methods.
We identify two critical types of quantized layers: those holding vital temporal information and those sensitive to reduced bit-width.
Our method is evaluated over three high-resolution image generation tasks and achieves state-of-the-art performance under various bit-width settings.
arXiv Detail & Related papers (2024-02-06T03:39:44Z) - FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models [16.940023904740585]
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.
arXiv Detail & Related papers (2023-12-06T14:24:26Z) - TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models [52.454274602380124]
Diffusion models heavily depend on the time-step $t$ to achieve satisfactory multi-round denoising.
We propose a Temporal Feature Maintenance Quantization (TFMQ) framework building upon a Temporal Information Block.
Powered by the pioneering block design, we devise temporal information aware reconstruction (TIAR) and finite set calibration (FSC) to align the full-precision temporal features.
arXiv Detail & Related papers (2023-11-27T12:59:52Z) - FormerTime: Hierarchical Multi-Scale Representations for Multivariate
Time Series Classification [53.55504611255664]
FormerTime is a hierarchical representation model for improving the classification capacity for the multivariate time series classification task.
It exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism.
arXiv Detail & Related papers (2023-02-20T07:46:14Z) - Gait Recognition in the Wild with Multi-hop Temporal Switch [81.35245014397759]
gait recognition in the wild is a more practical problem that has attracted the attention of the community of multimedia and computer vision.
This paper presents a novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes.
arXiv Detail & Related papers (2022-09-01T10:46:09Z) - STIP: A SpatioTemporal Information-Preserving and Perception-Augmented
Model for High-Resolution Video Prediction [78.129039340528]
We propose a Stemporal Information-Preserving and Perception-Augmented Model (STIP) to solve the above two problems.
The proposed model aims to preserve thetemporal information for videos during the feature extraction and the state transitions.
Experimental results show that the proposed STIP can predict videos with more satisfactory visual quality compared with a variety of state-of-the-art methods.
arXiv Detail & Related papers (2022-06-09T09:49:04Z)
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.