mlsanityData to 14 Oct 2026

UnrealNAS: Can We Search Neural Architectures with Unreal Data?

arXiv 2205.02162 ↗First posted 4 May 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural architecture search (NAS) has shown great success in the automatic design of deep neural networks (DNNs). However, the best way to use data to search network architectures is still unclear and under exploration. Previous work has analyzed the necessity of having ground-truth labels in NAS and inspired broad interest. In this work, we take a further step to question whether real data is necessary for NAS to be effective. The answer to this question is important for applications with limited amount of accessible data, and can help people improve NAS by leveraging the extra flexibility of data generation. To explore if NAS needs real data, we construct three types of unreal datasets using: 1) randomly labeled real images; 2) generated images and labels; and 3) generated Gaussian noise with random labels. These datasets facilitate to analyze the generalization and expressivity of the searched architectures. We study the performance of architectures searched on these constructed datasets using popular differentiable NAS methods. Extensive experiments on CIFAR, ImageNet and CheXpert show that the searched architectures can achieve promising results compared with those derived from the conventional NAS pipeline with real labeled data, suggesting the feasibility of performing NAS with unreal data.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 49 references that are in the map. First posted on arXiv 4 May 2022.

Builds on

44 of 49 references.

References · 44

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  2. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  3. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  4. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  5. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,352
  6. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  7. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  8. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  9. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  10. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  11. 2017Exploring Generalization in Deep Learningcited by 600
  12. 2017Progressive Neural Architecture Searchcited by 487
32 more
  1. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  2. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  3. 2016On the Expressive Power of Deep Neural Networkscited by 306
  4. 2018SNAS: Stochastic Neural Architecture Searchcited by 289
  5. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 269
  6. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 261
  7. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 260
  8. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 254
  9. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  10. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 202
  11. 2017Hierarchical Representations for Efficient Architecture Searchcited by 191
  12. 2018Sensitivity and Generalization in Neural Networks: an Empirical Studycited by 189
  13. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 178
  14. 2019Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Searchcited by 131
  15. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  16. 2021Pre-training without Natural Imagescited by 100
  17. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  18. 2019NAS evaluation is frustratingly hardcited by 70
  19. 2019SGAS: Sequential Greedy Architecture Searchcited by 69
  20. 2019BayesNAS: A Bayesian Approach for Neural Architecture Searchcited by 68
  21. 2020What Do Neural Networks Learn When Trained With Random Labels?cited by 59
  22. 2021CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretationcited by 57
  23. 2020Semi-Supervised Neural Architecture Searchcited by 46
  24. 2018Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Searchcited by 38
  25. 2020Are Labels Necessary for Neural Architecture Search?cited by 37
  26. 2019XNAS: Neural Architecture Search with Expert Advicecited by 35
  27. 2021Neural Architecture Search with Random Labelscited by 33
  28. 2020Neural Architecture Generator Optimizationcited by 30
  29. 2017On the ability of neural nets to express distributionscited by 26
  30. 2021HAO: Hardware-aware neural Architecture Optimization for Efficient Inferencecited by 16
  31. 2018Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-Learning Accuracycited by 14
  32. 2018Leveraging Random Label Memorization for Unsupervised Pre-Trainingcited by 12

Built on by

Not cited yet.