paper-with-me

Papers

MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer

2024-01-26 · Yu-Shan Tai, An-Yeu, Wu

While vision transformers (ViTs) have shown great potential in computer vision tasks, their intense computation and memory requirements pose challenges for practical applications. Existing post-training quantization methods leverage value redistribution or specialized quantizers to address the non-normal distribution in ViTs. However, without considering the asymmetry in activations and relying on hand-crafted settings, these methods often struggle to maintain performance under low-bit quantization. To overcome these challenges, we introduce SmoothQuant with bias term (SQ-b) to alleviate the asymmetry issue and reduce the clamping loss. We also introduce optimal scaling factor ratio search (OPT-m) to determine quantization parameters by a data-dependent mechanism automatically. To further enhance the compressibility, we incorporate the above-mentioned techniques and propose a mixed-precision post-training quantization framework for vision transformers (MPTQ-ViT). We develop greedy mixed-precision quantization (Greedy MP) to allocate layer-wise bit-width considering both model performance and compressibility. Our experiments on ViT, DeiT, and Swin demonstrate significant accuracy improvements compared with SOTA on the ImageNet dataset. Specifically, our proposed methods achieve accuracy improvements ranging from 0.90% to 23.35% on 4-bit ViTs with single-precision and from 3.82% to 78.14% on 5-bit fully quantized ViTs with mixed-precision.

📄 PDF Abstract BibTeX arXiv:2401.14895

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision

2020-02-20 · Xingchao Liu, Mao Ye, Dengyong Zhou, Qiang Liu

We consider the post-training quantization problem, which discretizes the weights of pre-trained deep neural networks without re-training the model. We propose multipoint quantization, a quantization method that approxim…

object-detectionObject DetectionQuantization

MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers

2026-07-30 · Md. Mehrab Hossain Opi, Robiul Islam Ryad, Md. Umar Faruk arxiv

Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices. However, existing PTQ methods typically employ uniform bit-widths across tra…

Instance SegmentationObject Detection

APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models

2024-02-21 · Ziyi Guan, Hantao Huang, Yupeng Su, Hong Huang 외

Large Language Models (LLMs) have greatly advanced the natural language processing paradigm. However, the high computational load and huge model sizes pose a grand challenge for deployment on edge devices. To this end, w…

Quantization

Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity

2025-01-10 · Navin Ranjan, Andreas Savakis

In this paper, we propose Mix-QViT, an explainability-driven MPQ framework that systematically allocates bit-widths to each layer based on two criteria: layer importance, assessed via Layer-wise Relevance Propagation (LR…

QuantizationSensitivity

Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search

2023-02-02 · Clemens JS Schaefer, Elfie Guo, Caitlin Stanton, Xiaofan Zhang 외

Serving large-scale machine learning (ML) models efficiently and with low latency has become challenging owing to increasing model size and complexity. Quantizing models can simultaneously reduce memory and compute requi…

QuantizationSensitivity