LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization

• URL: http://arxiv.org/abs/2411.17178v1
• Date: Tue, 26 Nov 2024 07:32:36 GMT
• Title: LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization
• Authors: Rui Xie, Tianchen Zhao, Zhihang Yuan, Rui Wan, Wenxi Gao, Zhenhua Zhu, Xuefei Ning, Yu Wang,
• Abstract summary: Current AR-based visual generation models require substantial computational resources, limiting their applicability on resource-constrained devices. We propose efficient attention mechanism and low-bit quantization method to enhance the efficiency of VAR models while maintaining performance.
• Score: 17.190984773586745
• License:
• Abstract: Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial computational resources, limiting their applicability on resource-constrained devices. To address this issue, we conducted analysis and identified significant redundancy in three dimensions of the VAR model: (1) the attention map, (2) the attention outputs when using classifier free guidance, and (3) the data precision. Correspondingly, we proposed efficient attention mechanism and low-bit quantization method to enhance the efficiency of VAR models while maintaining performance. With negligible performance lost (less than 0.056 FID increase), we could achieve 85.2% reduction in attention computation, 50% reduction in overall memory and 1.5x latency reduction. To ensure deployment feasibility, we developed efficient training-free compression techniques and analyze the deployment feasibility and efficiency gain of each technique.

Related papers

• ALOcc: Adaptive Lifting-based 3D Semantic Occupancy and Cost Volume-based Flow Prediction [89.89610257714006]
  Existing methods prioritize higher accuracy to cater to the demands of these tasks. We introduce a series of targeted improvements for 3D semantic occupancy prediction and flow estimation. Our purelytemporalal architecture framework, named ALOcc, achieves an optimal tradeoff between speed and accuracy.
  arXiv  Detail & Related papers  (2024-11-12T11:32:56Z)
• Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Model [0.14999444543328289]
  Ali-AUG is a novel single-step diffusion model for efficient labeled data augmentation in industrial applications. Our method addresses the challenge of limited labeled data by generating synthetic, labeled images with precise feature insertion.
  arXiv  Detail & Related papers  (2024-10-24T12:12:46Z)
• ReduceFormer: Attention with Tensor Reduction by Summation [4.985969607297595]
  We introduce ReduceFormer, a family of models optimized for efficiency with the spirit of attention. ReduceFormer leverages only simple operations such as reduction and element-wise multiplication, leading to greatly simplified architecture and improved inference performance. The proposed model family is suitable for edge devices where compute resource and memory bandwidth are limited, as well as for cloud computing where high throughput is sought after.
  arXiv  Detail & Related papers  (2024-06-11T17:28:09Z)
• LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights [2.8461446020965435]
  We introduce LD-Pruner, a novel performance-preserving structured pruning method for compressing Latent Diffusion Models. We demonstrate the effectiveness of our approach on three different tasks: text-to-image (T2I) generation, Unconditional Image Generation (UIG) and Unconditional Audio Generation (UAG)
  arXiv  Detail & Related papers  (2024-04-18T06:35:37Z)
• A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization [54.113083217869516]
  In this work, we first explore the computational redundancy part of the network. We then prune the redundancy blocks of the model and maintain the network performance. Thirdly, we propose a global-regional interactive (GRI) attention to speed up the computationally intensive attention part.
  arXiv  Detail & Related papers  (2023-12-24T15:37:47Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration [59.6021678234829]
  We propose a novel method to restore the intermediate features for two sparsely sampled and adjacent video frames. With the integration of our method, the efficiency of three commonly used baselines has been improved by over 50%, with a mere 0.5% reduction in recognition accuracy.
  arXiv  Detail & Related papers  (2023-07-27T13:52:42Z)
• How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction [66.09605613944201]
  We quantitatively evaluate the effect of attention and Knowledge Graph on bag-level relation extraction (RE) We find that (1) higher attention accuracy may lead to worse performance as it may harm the model's ability to extract entity mention features; (2) the performance of attention is largely influenced by various noise distribution patterns; and (3) KG-enhanced attention indeed improves RE performance, while not through enhanced attention but by incorporating entity prior.
  arXiv  Detail & Related papers  (2021-07-26T09:38:28Z)
• AttentionLite: Towards Efficient Self-Attention Models for Vision [9.957033392865982]
  We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. We can simultaneously distill knowledge from a compute-heavy teacher while also pruning the student model in a single pass of training.
  arXiv  Detail & Related papers  (2020-12-21T17:54:09Z)
• Towards Practical Lipreading with Distilled and Efficient Models [57.41253104365274]
  Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. There is still a significant gap between the current methodologies and the requirements for an effective deployment of lipreading in practical scenarios. We propose a series of innovations that significantly bridge that gap: first, we raise the state-of-the-art performance by a wide margin on LRW and LRW-1000 to 88.5% and 46.6%, respectively using self-distillation.
  arXiv  Detail & Related papers  (2020-07-13T16:56:27Z)

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.