Computer Vision Model Compression Techniques for Embedded Systems: A Survey

TL;DR

This survey reviews various model compression techniques for computer vision, focusing on enabling deployment of large neural networks on resource-constrained embedded systems, and provides practical guidance and case studies.

Contribution

It systematically compares compression approaches, discusses selection criteria, and shares implementation resources for deploying vision models on embedded devices.

Findings

Different compression techniques have unique trade-offs and suitability.

Guidelines help choose optimal compression methods for specific embedded hardware.

Case studies demonstrate practical application and effectiveness.

Abstract

Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when trained with plenty of representative data. With the recent adoption of Vision Transformer (ViT) based architectures and advanced Convolutional Neural Networks (CNNs), the total number of parameters of leading backbone architectures increased from 62M parameters in 2012 with AlexNet to 7B parameters in 2024 with AIM-7B. Consequently, deploying such deep architectures faces challenges in environments with processing and runtime constraints, particularly in embedded systems. This paper covers the main model compression techniques applied for computer vision tasks, enabling modern models to be used in embedded systems. We present the characteristics of compression subareas, compare different approaches, and discuss how to choose the best technique and expected variations when analyzing it on various embedded devices. We also share codes to assist researchers and new practitioners in overcoming initial implementation challenges for each subarea and present trends for Model Compression. Case studies for compression models are available at \href{https://github.com/venturusbr/cv-model-compression}{https://github.com/venturusbr/cv-model-compression}.