Computation-efficient Deep Learning for Computer Vision: A Survey

by   Yulin Wang, et al.

Over the past decade, deep learning models have exhibited considerable advancements, reaching or even exceeding human-level performance in a range of visual perception tasks. This remarkable progress has sparked interest in applying deep networks to real-world applications, such as autonomous vehicles, mobile devices, robotics, and edge computing. However, the challenge remains that state-of-the-art models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios. This trade-off between effectiveness and efficiency has catalyzed the emergence of a new research focus: computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference. This review offers an extensive analysis of this rapidly evolving field by examining four key areas: 1) the development of static or dynamic light-weighted backbone models for the efficient extraction of discriminative deep representations; 2) the specialized network architectures or algorithms tailored for specific computer vision tasks; 3) the techniques employed for compressing deep learning models; and 4) the strategies for deploying efficient deep networks on hardware platforms. Additionally, we provide a systematic discussion on the critical challenges faced in this domain, such as network architecture design, training schemes, practical efficiency, and more realistic model compression approaches, as well as potential future research directions.


page 1

page 2

page 3

page 4


Deep Learning Towards Edge Computing: Neural Networks Straight from Compressed Data

Due to the popularization and grow in computational power of mobile phon...

Challenges and Obstacles Towards Deploying Deep Learning Models on Mobile Devices

From computer vision and speech recognition to forecasting trajectories ...

Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey

Deep learning technologies have demonstrated remarkable effectiveness in...

Deep Learning Training Procedure Augmentations

Recent advances in Deep Learning have greatly improved performance on va...

Latency-aware Unified Dynamic Networks for Efficient Image Recognition

Dynamic computation has emerged as a promising avenue to enhance the inf...

Dynamic Neural Networks: A Survey

Dynamic neural network is an emerging research topic in deep learning. C...

Please sign up or login with your details

Forgot password? Click here to reset