mlsanityData to 14 Oct 2026

DeepliteRT: Computer Vision at the Edge

arXiv 2309.10878 ↗First posted 19 Sep 2023cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The proliferation of edge devices has unlocked unprecedented opportunities for deep learning model deployment in computer vision applications. However, these complex models require considerable power, memory and compute resources that are typically not available on edge platforms. Ultra low-bit quantization presents an attractive solution to this problem by scaling down the model weights and activations from 32-bit to less than 8-bit. We implement highly optimized ultra low-bit convolution operators for ARM-based targets that outperform existing methods by up to 4.34x. Our operator is implemented within Deeplite Runtime (DeepliteRT), an end-to-end solution for the compilation, tuning, and inference of ultra low-bit models on ARM devices. Compiler passes in DeepliteRT automatically convert a fake-quantized model in full precision to a compact ultra low-bit representation, easing the process of quantized model deployment on commodity hardware. We analyze the performance of DeepliteRT on classification and detection models against optimized 32-bit floating-point, 8-bit integer, and 2-bit baselines, achieving significant speedups of up to 2.20x, 2.33x and 2.17x, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

21 of 33 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  7. 2018YOLOv3: An Incremental Improvementcited by 2,659
  8. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  9. 2019Learned Step Size Quantizationcited by 628
  10. 2021A White Paper on Neural Network Quantizationcited by 472
  11. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  12. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
9 more
  1. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 274
  2. 2020Binary Neural Networks: A Surveycited by 190
  3. 2018Learning to Optimize Tensor Programscited by 140
  4. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  5. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 95
  6. 2020HAWQV3: Dyadic Neural Network Quantizationcited by 60
  7. 2020BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNscited by 21
  8. 2023DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tablescited by 8
  9. 2018Automating Generation of Low Precision Deep Learning Operatorscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime
  2. 2026DeVIT: Low-Power Vision Transformer Acceleration Using Delta Computation
  3. 2024Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey
  4. 2026SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness
  5. 2024ViT-1.58b: Mobile Vision Transformers in the 1-bit Era
  6. 2024Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
  7. 2025Low-bit Model Quantization for Deep Neural Networks: A Survey
  8. 2026Lightweight Transformer Architectures for Edge Devices in Real-Time Applications