InstaNAS: Instance-aware Neural Architecture Search

@inproceedings{Cheng2020InstaNASIN,
  title={InstaNAS: Instance-aware Neural Architecture Search},
  author={A. Cheng and Chieh Hubert Lin and Da-Cheng Juan and W. Wei and Min Sun},
  booktitle={AAAI},
  year={2020}
}
  • A. Cheng, Chieh Hubert Lin, +2 authors Min Sun
  • Published in AAAI 2020
  • Computer Science, Mathematics
  • Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuitively, electing domain-expert architectures that are proficient in domain-specific features can further benefit architecture related objectives such as latency. In this paper, we… CONTINUE READING
    12 Citations
    NASIB: Neural Architecture Search withIn Budget
    • PDF
    Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
    • 3
    • PDF
    Architecture Search by Estimation of Network Structure Distributions
    • PDF
    Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search
    • 10
    • PDF
    ISBNet: Instance-aware Selective Branching Network
    • 3
    Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization
    • PDF
    Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
    • Highly Influenced
    • PDF
    AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
    • 12
    • PDF
    FasterSeg: Searching for Faster Real-time Semantic Segmentation
    • 25
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 43 REFERENCES
    Multi-objective Architecture Search for CNNs
    • 48
    Efficient Neural Architecture Search via Parameter Sharing
    • 1,029
    • PDF
    HydraNets: Specialized Dynamic Architectures for Efficient Inference
    • 37
    • PDF
    Neural Architecture Search with Reinforcement Learning
    • 2,208
    • PDF
    Resource-Efficient Neural Architect
    • 30
    • PDF
    Learning Time/Memory-Efficient Deep Architectures with Budgeted Super Networks
    • Tom Veniat, Ludovic Denoyer
    • Computer Science, Mathematics
    • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • 2018
    • 46
    • PDF
    ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
    • 613
    • PDF
    MnasNet: Platform-Aware Neural Architecture Search for Mobile
    • 773
    • PDF
    MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
    • 57
    • PDF
    DARTS: Differentiable Architecture Search
    • 1,104
    • PDF