A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Miao, Wang, Lishun, Wang, Huan, Yuan, Xin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915398916505600
author Cao, Miao
Wang, Lishun
Wang, Huan
Yuan, Xin
author_facet Cao, Miao
Wang, Lishun
Wang, Huan
Yuan, Xin
contents Video Snapshot Compressive Imaging (SCI) aims to use a low-speed 2D camera to capture high-speed scene as snapshot compressed measurements, followed by a reconstruction algorithm to reconstruct the high-speed video frames. State-of-the-art (SOTA) deep learning-based algorithms have achieved impressive performance, yet with heavy computational workload. Network quantization is a promising way to reduce computational cost. However, a direct low-bit quantization will bring large performance drop. To address this challenge, in this paper, we propose a simple low-bit quantization framework (dubbed Q-SCI) for the end-to-end deep learning-based video SCI reconstruction methods which usually consist of a feature extraction, feature enhancement, and video reconstruction module. Specifically, we first design a high-quality feature extraction module and a precise video reconstruction module to extract and propagate high-quality features in the low-bit quantized model. In addition, to alleviate the information distortion of the Transformer branch in the quantized feature enhancement module, we introduce a shift operation on the query and key distributions to further bridge the performance gap. Comprehensive experimental results manifest that our Q-SCI framework can achieve superior performance, e.g., 4-bit quantized EfficientSCI-S derived by our Q-SCI framework can theoretically accelerate the real-valued EfficientSCI-S by 7.8X with only 2.3% performance gap on the simulation testing datasets. Code is available at https://github.com/mcao92/QuantizedSCI.
format Preprint
id arxiv_https___arxiv_org_abs_2407_21517
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging
Cao, Miao
Wang, Lishun
Wang, Huan
Yuan, Xin
Computer Vision and Pattern Recognition
Video Snapshot Compressive Imaging (SCI) aims to use a low-speed 2D camera to capture high-speed scene as snapshot compressed measurements, followed by a reconstruction algorithm to reconstruct the high-speed video frames. State-of-the-art (SOTA) deep learning-based algorithms have achieved impressive performance, yet with heavy computational workload. Network quantization is a promising way to reduce computational cost. However, a direct low-bit quantization will bring large performance drop. To address this challenge, in this paper, we propose a simple low-bit quantization framework (dubbed Q-SCI) for the end-to-end deep learning-based video SCI reconstruction methods which usually consist of a feature extraction, feature enhancement, and video reconstruction module. Specifically, we first design a high-quality feature extraction module and a precise video reconstruction module to extract and propagate high-quality features in the low-bit quantized model. In addition, to alleviate the information distortion of the Transformer branch in the quantized feature enhancement module, we introduce a shift operation on the query and key distributions to further bridge the performance gap. Comprehensive experimental results manifest that our Q-SCI framework can achieve superior performance, e.g., 4-bit quantized EfficientSCI-S derived by our Q-SCI framework can theoretically accelerate the real-valued EfficientSCI-S by 7.8X with only 2.3% performance gap on the simulation testing datasets. Code is available at https://github.com/mcao92/QuantizedSCI.
title A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.21517