mlsanityData to 7 Oct 2026

NAS-BNN: Neural Architecture Search for Binary Neural Networks

arXiv 2408.15484 ↗First posted 28 Aug 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a powerful binary architecture is challenging and often requires significant manpower. A promising solution is to utilize Neural Architecture Search (NAS) to assist in designing BNNs, but current NAS methods for BNNs are relatively straightforward and leave a performance gap between the searched models and manually designed ones. To address this gap, we propose a novel neural architecture search scheme for binary neural networks, named NAS-BNN. We first carefully design a search space based on the unique characteristics of BNNs. Then, we present three training strategies, which significantly enhance the training of supernet and boost the performance of all subnets. Our discovered binary model family outperforms previous BNNs for a wide range of operations (OPs) from 20M to 200M. For instance, we achieve 68.20% top-1 accuracy on ImageNet with only 57M OPs. In addition, we validate the transferability of these searched BNNs on the object detection task, and our binary detectors with the searched BNNs achieve a novel state-of-the-art result, e.g., 31.6% mAP with 370M OPs, on MS COCO dataset. The source code and models will be released at https://github.com/VDIGPKU/NAS-BNN.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 53 references that are in the map. First posted on arXiv 28 Aug 2024.

Builds on

43 of 53 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  5. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  6. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  7. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  8. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  9. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  10. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  11. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  12. 2019Learned Step Size Quantizationcited by 604
31 more
  1. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  2. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  3. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  4. 2019Universally Slimmable Networks and Improved Training Techniquescited by 219
  5. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 200
  6. 2017Hierarchical Representations for Efficient Architecture Searchcited by 188
  7. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 187
  8. 2020Binary Neural Networks: A Surveycited by 184
  9. 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 183
  10. 2019Forward and Backward Information Retention for Accurate Binary Neural Networkscited by 169
  11. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  12. 2019Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscited by 143
  13. 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 122
  14. 2020Training Binary Neural Networks with Real-to-Binary Convolutionscited by 111
  15. 2020APQ: Joint Search for Network Architecture, Pruning and Quantization Policycited by 98
  16. 2020AttentiveNAS: Improving Neural Architecture Search via Attentive Samplingcited by 65
  17. 2021AlphaNet: Improved Training of Supernets with Alpha-Divergencecited by 36
  18. 2020BiDet: An Efficient Binarized Object Detectorcited by 33
  19. 2020MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?cited by 32
  20. 2020BiPointNet: Binary Neural Network for Point Cloudscited by 30
  21. 2020BATS: Binary ArchitecTure Searchcited by 26
  22. 2019Improved training of binary networks for human pose estimation and image recognitioncited by 22
  23. 2020Binarizing MobileNet via Evolution-based Searchingcited by 21
  24. 2021BatchQuant: Quantized-for-all Architecture Search with Robust Quantizercited by 19
  25. 2019MoBiNet: A Mobile Binary Network for Image Classificationcited by 15
  26. 2020Controlling Information Capacity of Binary Neural Networkcited by 15
  27. 2020Learning Architectures for Binary Networkscited by 13
  28. 2020NASB: Neural Architecture Search for Binary Convolutional Neural Networkscited by 8
  29. 2020BCNN: A Binary CNN with All Matrix Ops Quantized to 1 Bit Precisioncited by 6
  30. 2021Learning Deep Morphological Networks with Neural Architecture Searchcited by 6
  31. 2020BARS: Joint Search of Cell Topology and Layout for Accurate and Efficient Binary ARchitecturescited by 3

Built on by

Not cited yet.