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.

翻译：可微分架构搜索（DARTS）作为一种基于梯度的神经架构搜索方法已引起广泛关注。自DARTS提出以来，基于最先进的CNN架构设计原则对动作空间进行适配的工作尚显不足。本研究旨在通过借鉴ConvNeXt理念的微设计变化逐步扩展DARTS搜索空间，并探索精度、评估层数与计算成本之间的权衡。我们提出了伪逆瓶颈卷积模块（PIBConv），旨在降低ConvNeXt中提出的逆瓶颈模块的计算开销。所提架构对评估层数的敏感度显著降低，在仅包含2层网络时，其性能即显著优于同等规模的DARTS网络。此外，在层数更少的情况下，该方法不仅能以更低计算量（以GMACs衡量）和参数量获得更高精度，GradCAM对比结果还显示，相较于DARTS，我们的网络能更有效地检测目标对象的区分性特征。代码已发布于https://github.com/mahdihosseini/PIBConv。