mlsanityData to 7 Oct 2026

DAAS: Differentiable Architecture and Augmentation Policy Search

arXiv 2109.15273 ↗First posted 30 Sep 2021cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures. The searched architecture is evaluated by training on datasets with fixed data augmentation policies. However, recent works on auto-augmentation show that the suited augmentation policies can vary over different structures. Therefore, this work considers the possible coupling between neural architectures and data augmentation and proposes an effective algorithm jointly searching for them. Specifically, 1) for the NAS task, we adopt a single-path based differentiable method with Gumbel-softmax reparameterization strategy due to its memory efficiency; 2) for the auto-augmentation task, we introduce a novel search method based on policy gradient algorithm, which can significantly reduce the computation complexity. Our approach achieves 97.91% accuracy on CIFAR-10 and 76.6% Top-1 accuracy on ImageNet dataset, showing the outstanding performance of our search algorithm.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

27 of 33 references.

References · 27

  1. 2016Wide Residual Networkscited by 3,057
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  3. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  4. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  5. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  6. 2017Progressive Neural Architecture Searchcited by 483
  7. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  8. 2018SNAS: Stochastic Neural Architecture Searchcited by 288
  9. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  10. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 258
  11. 2019Fast AutoAugmentcited by 243
  12. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
15 more
  1. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 176
  2. 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 175
  3. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  4. 2019Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Searchcited by 129
  5. 2020Stabilizing Differentiable Architecture Search via Perturbation-based Regularizationcited by 102
  6. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  7. 2020DARTS-: Robustly Stepping out of Performance Collapse Without Indicatorscited by 81
  8. 2019Tabular Benchmarks for Joint Architecture and Hyperparameter Optimizationcited by 57
  9. 2018ShakeDrop Regularization for Deep Residual Learningcited by 40
  10. 2018Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Searchcited by 38
  11. 2020FBNetV3: Joint Architecture-Recipe Search using Predictor Pretrainingcited by 35
  12. 2021Direct Differentiable Augmentation Searchcited by 28
  13. 2020AutoHAS: Efficient Hyperparameter and Architecture Searchcited by 8
  14. 2021DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecturecited by 6
  15. 2020Joint Search of Data Augmentation Policies and Network Architecturescited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 2.

4 papers.

  1. 2023SLACK: Stable Learning of Augmentations with Cold-start and KL regularizationcited by 6
  2. 2022Multi-Agent Automated Machine Learningcited by 3
  3. 2024FreeAugment: Data Augmentation Search Across All Degrees of Freedomcited by 3
  4. 2024Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methodscited by 1