mlsanityData to 14 Oct 2026

Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge

arXiv 2401.12350 ↗First posted 22 Jan 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural Architecture Search (NAS) has become the de-facto approach for designing accurate and efficient networks for edge devices. Since models are typically quantized for edge deployment, recent work has investigated quantization-aware NAS (QA-NAS) to search for highly accurate and efficient quantized models. However, existing QA-NAS approaches, particularly few-bit mixed-precision (FB-MP) methods, do not scale to larger tasks. Consequently, QA-NAS has mostly been limited to low-scale tasks and tiny networks. In this work, we present an approach to enable QA-NAS (INT8 and FB-MP) on large-scale tasks by leveraging the block-wise formulation introduced by block-wise NAS. We demonstrate strong results for the semantic segmentation task on the Cityscapes dataset, finding FB-MP models 33% smaller and INT8 models 17.6% faster than DeepLabV3 (INT8) without compromising task performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 22 Jan 2024.

Builds on

20 of 27 references.

References · 20

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  3. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  4. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  5. 2020Knowledge Distillation: A Surveycited by 1,603
  6. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  7. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  8. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  9. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  10. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 130
  11. 2020APQ: Joint Search for Network Architecture, Pruning and Quantization Policycited by 99
  12. 2019Blockwisely Supervised Neural Architecture Search with Knowledge Distillationcited by 81
8 more
  1. 2020Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectorscited by 80
  2. 2016SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Drivingcited by 55
  3. 2020Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gapcited by 50
  4. 2020Distilling Optimal Neural Networks: Rapid Search in Diverse Spacescited by 32
  5. 2021BatchQuant: Quantized-for-all Architecture Search with Robust Quantizercited by 20
  6. 2020FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Searchcited by 17
  7. 2022Neural Architecture Search for Energy Efficient Always-on Audio Modelscited by 5
  8. 2023BOMP-NAS: Bayesian Optimization Mixed Precision NAScited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search
  2. 2022HQNAS: Auto CNN deployment framework for joint quantization and architecture search
  3. 2022Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes
  4. 2026LLM Compression with Jointly Optimizing Architectural and Quantization choices
  5. 2026NAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space
  6. 2025On Accelerating Edge AI: Optimizing Resource-Constrained Environments
  7. 2026RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models
  8. 2023Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge