The paper proposes CSCO, a novel paradigm that allows flexible exploration of the dense connectivity of building operators and innovates building cells in CNN architectures. CSCO represents the CNN architecture as a meta-graph comprising multiple Directed Acyclic Graphs (DAGs), where each DAG represents a building cell with dense connectivity of versatile convolutional operators.
To enhance the reliability and quality of prediction during the search, the paper introduces two key techniques:
Graph Isomorphism: This is used as data augmentation to boost sample efficiency and improve the accuracy of the performance predictor without additional search cost.
Metropolis-Hastings Evolutionary Search (MH-ES): This is proposed as an efficient search strategy to explore the dense connectivity design space and effectively evade locally optimal solutions.
Experiments on the ImageNet dataset show that CSCO can discover CNN architectures that outperform existing hand-crafted and NAS-crafted dense connectivity designs by around 0.6% in top-1 accuracy under mobile computation regimes.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Tunhou Zhang... at arxiv.org 04-29-2024
https://arxiv.org/pdf/2404.17152.pdfDeeper Inquiries