DARTS搜索空间的伪反向瓶颈卷积
Pseudo-Inverted Bottleneck Convolution for DARTS Search Space
摘要：
可区分结构搜索（DARTS）作为一种基于梯度的神经结构搜索方法已经引起了相当大的关注。自DARTS引入以来，基于CNN最先进的架构设计原则，在调整动作空间方面所做的工作很少。在这项工作中，我们的目标是解决这一差距，增量增加DARTS搜索空间与微设计的变化，灵感来自ConvNeXt和研究之间的权衡精度，评估层数和计算成本。我们引入伪反向瓶颈转换（PIBConv）块，旨在减少ConvNeXt中提出的反向瓶颈块的计算占用空间。我们提出的架构对评估层数不太敏感，并且在层数小到2的情况下显著优于具有类似大小的DARTS网络。此外，通过更少的层，它不仅可以实现更高的准确性和更低的计算占用（以GMAC测量）和参数计数，GradCAM比较表明，与DARTS相比，我们的网络可以更好地检测目标对象的独特特征。代码可从www.example.com获得。
英文摘要：
Differentiable Architecture Search (DARTS) has attracted considerable attention as a gradient-based neural architecture search method. Since the introduction of DARTS, there has been little work done on adapting the action space based on state-of-art architecture design principles for CNNs. In this work, we aim to address this gap by incrementally augmenting the DARTS search space with micro-design changes inspired by ConvNeXt and studying the trade-off between accuracy, evaluation layer count, and computational cost. We introduce the Pseudo-Inverted Bottleneck Conv (PIBConv) block intending to reduce the computational footprint of the inverted bottleneck block proposed in ConvNeXt. Our proposed architecture is much less sensitive to evaluation layer count and outperforms a DARTS network with similar size significantly, at layer counts as small as 2. Furthermore, with less layers, not only does it achieve higher accuracy with lower computational footprint (measured in GMACs) and parameter count, GradCAM comparisons show that our network can better detect distinctive features of target objects compared to DARTS. Code is available from https://github.com/mahdihosseini/PIBConv.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
