mlsanityData to 14 Oct 2026

PredNAS: A Universal and Sample Efficient Neural Architecture Search Framework

arXiv 2210.14460 ↗First posted 26 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a general and effective framework for Neural Architecture Search (NAS), named PredNAS. The motivation is that given a differentiable performance estimation function, we can directly optimize the architecture towards higher performance by simple gradient ascent. Specifically, we adopt a neural predictor as the performance predictor. Surprisingly, PredNAS can achieve state-of-the-art performances on NAS benchmarks with only a few training samples (less than 100). To validate the universality of our method, we also apply our method on large-scale tasks and compare our method with RegNet on ImageNet and YOLOX on MSCOCO. The results demonstrate that our PredNAS can explore novel architectures with competitive performances under specific computational complexity constraints.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

41 of 53 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  7. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  8. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  9. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  10. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  11. 2020Designing Network Design Spacescited by 960
  12. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
29 more
  1. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  2. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  3. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  4. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  5. 2017Progressive Neural Architecture Searchcited by 487
  6. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 470
  7. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  8. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  9. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  10. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 291
  11. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 260
  12. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  13. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 188
  14. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 178
  15. 2018Neural Architecture Optimizationcited by 167
  16. 2019Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Searchcited by 131
  17. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 130
  18. 2019Neural Predictor for Neural Architecture Searchcited by 118
  19. 2020Stabilizing Differentiable Architecture Search via Perturbation-based Regularizationcited by 102
  20. 2020NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Sizecited by 98
  21. 2019DetNAS: Backbone Search for Object Detectioncited by 81
  22. 2019NAS-FCOS: Fast Neural Architecture Search for Object Detectioncited by 53
  23. 2019SpineNet: Learning Scale-Permuted Backbone for Recognition and Localizationcited by 50
  24. 2019ReNAS:Relativistic Evaluation of Neural Architecture Searchcited by 37
  25. 2020FBNetV3: Joint Architecture-Recipe Search using Predictor Pretrainingcited by 35
  26. 2020Angle-based Search Space Shrinking for Neural Architecture Searchcited by 32
  27. 2017Peephole: Predicting Network Performance Before Trainingcited by 23
  28. 2018You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimizationcited by 23
  29. 2021Homogeneous Architecture Augmentation for Neural Predictorcited by 14

Built on by

Not cited yet.