mlsanityData to 14 Oct 2026

Neural Architecture Search in operational context: a remote sensing case-study

arXiv 2109.08028 ↗First posted 15 Sep 2021cs.CV cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning has become in recent years a cornerstone tool fueling key innovations in the industry, such as autonomous driving. To attain good performances, the neural network architecture used for a given application must be chosen with care. These architectures are often handcrafted and therefore prone to human biases and sub-optimal selection. Neural Architecture Search (NAS) is a framework introduced to mitigate such risks by jointly optimizing the network architectures and its weights. Albeit its novelty, it was applied on complex tasks with significant results - e.g. semantic image segmentation. In this technical paper, we aim to evaluate its ability to tackle a challenging operational task: semantic segmentation of objects of interest in satellite imagery. Designing a NAS framework is not trivial and has strong dependencies to hardware constraints. We therefore motivate our NAS approach selection and provide corresponding implementation details. We also present novel ideas to carry out other such use-case studies.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 15 Sep 2021.

Builds on

26 of 35 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  4. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  7. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  8. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  9. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  10. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  11. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 279
  12. 2018Horovod: fast and easy distributed deep learning in TensorFlowcited by 279
14 more
  1. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  2. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 260
  3. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 254
  4. 2020Neural Architecture Search without Trainingcited by 244
  5. 2017Hierarchical Representations for Efficient Architecture Searchcited by 191
  6. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 178
  7. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 169
  8. 2018Efficient Multi-objective Neural Architecture Search via Lamarckian Evolutioncited by 153
  9. 2020A Survey on Evolutionary Neural Architecture Searchcited by 142
  10. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  11. 2019DARTS+: Improved Differentiable Architecture Search with Early Stoppingcited by 105
  12. 2019A Survey on Neural Architecture Searchcited by 71
  13. 2018Automated Machine Learning: From Principles to Practicescited by 62
  14. 2020Geometry-Aware Gradient Algorithms for Neural Architecture Searchcited by 40

Built on by

Not cited yet.