Patch-wise Mixed-Precision Quantization of Vision Transformer

• URL: http://arxiv.org/abs/2305.06559v1
• Date: Thu, 11 May 2023 04:34:10 GMT
• Title: Patch-wise Mixed-Precision Quantization of Vision Transformer
• Authors: Junrui Xiao, Zhikai Li, Lianwei Yang and Qingyi Gu
• Abstract summary: Vision Transformers (ViTs) require complex self-attention computation to guarantee the learning of powerful feature representations. We propose a novel patch-wise mixed-precision quantization (PMQ) for efficient inference of ViTs.
• Score: 2.3104000011280403
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As emerging hardware begins to support mixed bit-width arithmetic computation, mixed-precision quantization is widely used to reduce the complexity of neural networks. However, Vision Transformers (ViTs) require complex self-attention computation to guarantee the learning of powerful feature representations, which makes mixed-precision quantization of ViTs still challenging. In this paper, we propose a novel patch-wise mixed-precision quantization (PMQ) for efficient inference of ViTs. Specifically, we design a lightweight global metric, which is faster than existing methods, to measure the sensitivity of each component in ViTs to quantization errors. Moreover, we also introduce a pareto frontier approach to automatically allocate the optimal bit-precision according to the sensitivity. To further reduce the computational complexity of self-attention in inference stage, we propose a patch-wise module to reallocate bit-width of patches in each layer. Extensive experiments on the ImageNet dataset shows that our method greatly reduces the search cost and facilitates the application of mixed-precision quantization to ViTs.

Related papers

• PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution [87.89013794655207]
  Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. We propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR. Our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR.
  arXiv  Detail & Related papers  (2024-11-26T04:49:42Z)
• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer [54.713778961605115]
  Vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. We propose a novel non-uniform quantizer, dubbed the Adaptive Logarithm AdaLog (AdaLog) quantizer.
  arXiv  Detail & Related papers  (2024-07-17T18:38:48Z)
• MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer [7.041718444626999]
  We propose a mixed-precision post-training quantization framework for vision transformers (MPTQ-ViT) Our experiments on ViT, DeiT, and Swin demonstrate significant accuracy improvements compared with SOTA on the ImageNet dataset.
  arXiv  Detail & Related papers  (2024-01-26T14:25:15Z)
• CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers [12.987397453149537]
  We find a way to improve the accuracy of networks that have already been quantized, simply by perturbing the quantization scales. CTP-V contrasts the features of quantized and full precision models in a self-supervised fashion. It improves the top-1 accuracy of a fully quantized ViT-Base by 10.30%, 0.78%, and 0.15% for 3-bit, 4-bit, and 8-bit weight quantization levels.
  arXiv  Detail & Related papers  (2022-11-17T16:41:31Z)
• AMED: Automatic Mixed-Precision Quantization for Edge Devices [3.5223695602582614]
  Quantized neural networks are well known for reducing the latency, power consumption, and model size without significant harm to the performance. Mixed-precision quantization offers better utilization of customized hardware that supports arithmetic operations at different bitwidths.
  arXiv  Detail & Related papers  (2022-05-30T21:23:22Z)
• AdaViT: Adaptive Tokens for Efficient Vision Transformer [91.88404546243113]
  We introduce AdaViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. AdaViT achieves this by automatically reducing the number of tokens in vision transformers that are processed in the network as inference proceeds.
  arXiv  Detail & Related papers  (2021-12-14T18:56:07Z)
• Mixed Precision of Quantization of Transformer Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Current low-bit quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of the system to quantization errors. The optimal local precision settings are automatically learned using two techniques. Experiments conducted on Penn Treebank (PTB) and a Switchboard corpus trained LF-MMI TDNN system.
  arXiv  Detail & Related papers  (2021-11-29T09:57:00Z)
• Understanding and Overcoming the Challenges of Efficient Transformer Quantization [17.05322956052278]
  Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on resource-limited devices. We show that transformers have unique quantization challenges -- namely, high dynamic activation ranges that are difficult to represent with a low bit fixed-point format.
  arXiv  Detail & Related papers  (2021-09-27T10:57:18Z)
• Post-Training Quantization for Vision Transformer [85.57953732941101]
  We present an effective post-training quantization algorithm for reducing the memory storage and computational costs of vision transformers. We can obtain an 81.29% top-1 accuracy using DeiT-B model on ImageNet dataset with about 8-bit quantization.
  arXiv  Detail & Related papers  (2021-06-27T06:27:22Z)
• Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization [45.22093693422085]
  Mixed-precision quantization model can match different quantization bit-precisions according to the sensitivity of different layers to achieve great performance. It is a difficult problem to quickly determine the quantization bit-precision of each layer in deep neural networks according to some constraints. We propose a novel sequential single path search (SSPS) method for mixed-precision quantization.
  arXiv  Detail & Related papers  (2021-03-04T09:15:08Z)

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.