mlsanityData to 7 Oct 2026

MatchNAS: Optimizing Edge AI in Sparse-Label Data Contexts via Automating Deep Neural Network Porting for Mobile Deployment

arXiv 2402.13525 ↗First posted 21 Feb 2024cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent years have seen the explosion of edge intelligence with powerful Deep Neural Networks (DNNs). One popular scheme is training DNNs on powerful cloud servers and subsequently porting them to mobile devices after being lightweight. Conventional approaches manually specialized DNNs for various edge platforms and retrain them with real-world data. However, as the number of platforms increases, these approaches become labour-intensive and computationally prohibitive. Additionally, real-world data tends to be sparse-label, further increasing the difficulty of lightweight models. In this paper, we propose MatchNAS, a novel scheme for porting DNNs to mobile devices. Specifically, we simultaneously optimise a large network family using both labelled and unlabelled data and then automatically search for tailored networks for different hardware platforms. MatchNAS acts as an intermediary that bridges the gap between cloud-based DNNs and edge-based DNNs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

28 of 46 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  5. 2019Searching for MobileNetV3cited by 1,984
  6. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  8. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  9. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  10. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  11. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  12. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
16 more
  1. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  2. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  3. 2017Large-Scale Evolution of Image Classifierscited by 348
  4. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
  5. 2014Learning with Pseudo-Ensemblescited by 241
  6. 2020Neural Architecture Search without Trainingcited by 241
  7. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 187
  8. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 168
  9. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  10. 2017MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networkscited by 92
  11. 2018ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptationcited by 76
  12. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 71
  13. 2020GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernetcited by 69
  14. 2020AttentiveNAS: Improving Neural Architecture Search via Attentive Samplingcited by 65
  15. 2018A First Look at Deep Learning Apps on Smartphonescited by 47
  16. 2021CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deploymentcited by 26

Built on by

Not cited yet.