mlsanityData to 14 Oct 2026

Accelerator-aware Neural Network Design using AutoML

arXiv 2003.02838 ↗First posted 5 Mar 2020eess.SP cs.LG stat.MLcited by 30

Not on the map. Why?

Abstract (arXiv)

While neural network hardware accelerators provide a substantial amount of raw compute throughput, the models deployed on them must be co-designed for the underlying hardware architecture to obtain the optimal system performance. We present a class of computer vision models designed using hardware-aware neural architecture search and customized to run on the Edge TPU, Google's neural network hardware accelerator for low-power, edge devices. For the Edge TPU in Coral devices, these models enable real-time image classification performance while achieving accuracy typically seen only with larger, compute-heavy models running in data centers. On Pixel 4's Edge TPU, these models improve the accuracy-latency tradeoff over existing SoTA mobile models.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 8; 2023: 7; 2024: 6.

30 papers.

Sort:

By area:

  1. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  2. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 61
  3. 2023Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Modelscited by 44
  4. 2024Lightweight Deep Learning for Resource-Constrained Environments: A Surveycited by 38
  5. 2021Data-Driven Offline Optimization For Architecting Hardware Acceleratorscited by 29
  6. 2021Apollo: Transferable Architecture Explorationcited by 17
  7. 2021Rethinking Co-design of Neural Architectures and Hardware Acceleratorscited by 12
  8. 2023Towards Environmentally Equitable AI via Geographical Load Balancingcited by 10
  9. 2023CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centerscited by 6
  10. 2022Searching for Efficient Neural Architectures for On-Device ML on Edge TPUscited by 4
  11. 2022QAPPA: Quantization-Aware Power, Performance, and Area Modeling of DNN Acceleratorscited by 4
  12. 2023PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devicescited by 4
18 more
  1. 2024Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Acceleratorscited by 4
  2. 2024Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrievalcited by 4
  3. 2021Deep Learning on Edge TPUscited by 3
  4. 2022QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimalitycited by 3
  5. 2021FuSeConv: Fully Separable Convolutions for Fast Inference on Systolic Arrayscited by 2
  6. 2022U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Searchcited by 2
  7. 2022Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Searchcited by 2
  8. 2022QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Explorationcited by 2
  9. 2021Design and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edgecited by 1
  10. 2021ISyNet: Convolutional Neural Networks design for AI acceleratorcited by 1
  11. 2022Hardware-aware mobile building block evaluation for computer visioncited by 1
  12. 2023SequeL: A Continual Learning Library in PyTorch and JAXcited by 1
  13. 2023Comparison between transformers and convolutional models for fine-grained classification of insectscited by 1
  14. 2024Performance of computer vision algorithms for fine-grained classification using crowdsourced insect imagescited by 1
  15. 2022Tech Report: One-stage Lightweight Object Detectorscited by 0
  16. 2023Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Explorationcited by 0
  17. 2024Accel-NASBench: Sustainable Benchmarking for Accelerator-Aware NAScited by 0
  18. 2024Efficient Deep Learning Board: Training Feedback Is Not All You Needcited by 0