One-Shot Neural Architecture Search via Self-Evaluated Template Network

  title={One-Shot Neural Architecture Search via Self-Evaluated Template Network},
  author={Xuanyi Dong and Yezhou Yang},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  • Xuanyi Dong, Yezhou Yang
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Neural architecture search (NAS) aims to automate the search procedure of architecture instead of manual design. Even if recent NAS approaches finish the search within days, lengthy training is still required for a specific architecture candidate to get the parameters for its accurate evaluation. Recently one-shot NAS methods are proposed to largely squeeze the tedious training process by sharing parameters across candidates. In this way, the parameters for each candidate can be directly… CONTINUE READING
    33 Citations

    Figures, Tables, and Topics from this paper.

    Few-shot Neural Architecture Search
    • 2
    • Highly Influenced
    • PDF
    One-Shot Neural Architecture Search: Maximising Diversity to Overcome Catastrophic Forgetting.
    MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning
    • 8
    • PDF
    A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
    • 11
    • Highly Influenced
    • PDF
    FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
    AdversarialNAS: Adversarial Neural Architecture Search for GANs
    • 16
    • PDF
    NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
    • 57
    • Highly Influenced
    • PDF
    Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap


    Efficient Architecture Search by Network Transformation
    • 277
    Progressive Neural Architecture Search
    • 780
    • Highly Influential
    • PDF
    Neural Architecture Search with Reinforcement Learning
    • 2,068
    • Highly Influential
    • PDF
    Efficient Neural Architecture Search via Parameter Sharing
    • 946
    • Highly Influential
    • PDF
    SMASH: One-Shot Model Architecture Search through HyperNetworks
    • 341
    • Highly Influential
    • PDF
    Learning Transferable Architectures for Scalable Image Recognition
    • 1,945
    • Highly Influential
    • PDF
    SNAS: Stochastic Neural Architecture Search
    • 320
    • PDF
    Aggregated Residual Transformations for Deep Neural Networks
    • 2,887
    • PDF