mlsanityData to 7 Oct 2026

A Survey of Methods for Low-Power Deep Learning and Computer Vision

arXiv 2003.11066 ↗First posted 24 Mar 2020cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 10; 2023: 10; 2024: 8; 2025: 3; 2026: 1.

37 papers.

Sort:

By area:

  1. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  2. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classificationcited by 64
  3. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  4. 2023Fixing Overconfidence in Dynamic Neural Networkscited by 19
  5. 2023Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Visioncited by 11
  6. 2024Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Frameworkcited by 10
  7. 2023Guaranteed Approximation Bounds for Mixed-Precision Neural Operatorscited by 9
  8. 2021Spiking-GAN: A Spiking Generative Adversarial Network Using Time-To-First-Spike Codingcited by 8
  9. 2022Efficient Adaptive Ensembling for Image Classificationcited by 8
  10. 2024Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edgecited by 8
  11. 2022Flexible and Hierarchical Prior for Bayesian Nonnegative Matrix Factorizationcited by 7
  12. 2023Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networkscited by 7
25 more
  1. 2023DSD2: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?cited by 6
  2. 2022Bayesian Low-Rank Interpolative Decomposition for Complex Datasetscited by 4
  3. 2024A Plug-in Tiny AI Module for Intelligent and Selective Sensor Data Transmissioncited by 4
  4. 2021Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrievingcited by 3
  5. 2024BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Accelerationcited by 3
  6. 2021Efficient Computer Vision on Edge Devices with Pipeline-Parallel Hierarchical Neural Networkscited by 2
  7. 2022Software Engineering Approaches for TinyML based IoT Embedded Vision: A Systematic Literature Reviewcited by 2
  8. 2022Comparative Study of Inference Methods for Interpolative Decompositioncited by 2
  9. 2024Impact of ML Optimization Tactics on Greener Pre-Trained ML Modelscited by 2
  10. 2024Reducing Inference Energy Consumption Using Dual Complementary CNNscited by 2
  11. 2021Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networkscited by 1
  12. 2022Chemical transformer compression for accelerating both training and inference of molecular modelingcited by 1
  13. 2024Computer Vision Model Compression Techniques for Embedded Systems: A Surveycited by 1
  14. 2021Towards End-to-End Neural Face Authentication in the Wild -- Quantifying and Compensating for Directional Lighting Effectscited by 0
  15. 2022Efficient visual object representation using a biologically plausible spike-latency code and winner-take-all inhibitioncited by 0
  16. 2022Land Classification in Satellite Images by Injecting Traditional Features to CNN Modelscited by 0
  17. 2023Application for White Spot Syndrome Virus (WSSV) Monitoring using Edge Machine Learningcited by 0
  18. 2023On the fly Deep Neural Network Optimization Control for Low-Power Computer Visioncited by 0
  19. 2023Energy Concerns with HPC Systems and Applicationscited by 0
  20. 2023An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutionscited by 0
  21. 2024A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNscited by 0
  22. 2025SHARDeg: A Benchmark for Skeletal Human Action Recognition in Degraded Scenarioscited by 0
  23. 2025Adaptive Spiking with Plasticity for Energy Aware Neuromorphic Systemscited by 0
  24. 2025Dimension vs. Precision: A Comparative Analysis of Autoencoders and Quantization for Efficient Vector Retrieval on BEIR SciFactcited by 0
  25. 2026Tiny Collaborative Inference for Occlusion-Robust Object Detectioncited by 0