Binary Neural Networks (BNNs) have received significant attention due to their promising efficiency. Currently, most BNN studies directly adopt widely-used CNN architectures, which can be suboptimal for BNNs. This paper proposes a novel Binary ARchitecture Search (BARS) flow to discover superior binary architecture in a large design space. Specifically, we design a two-level (Macro \& Micro) search space tailored for BNNs and apply a differentiable neural architecture search (NAS) to explore this search space efficiently. The macro-level search space includes depth and width decisions, which is required for better balancing the model performance and capacity. And we also make modifications to the micro-level search space to strengthen the information flow for BNN. A notable challenge of BNN architecture search lies in that binary operations exacerbate the "collapse" problem of differentiable NAS, and we incorporate various search and derive strategies to stabilize the search process. On CIFAR-10, \method achieves $1.5\%$ higher accuracy with $2/3$ binary Ops and $1/10$ floating-point Ops. On ImageNet, with similar resource consumption, \method-discovered architecture achieves $3\%$ accuracy gain than hand-crafted architectures, while removing the full-precision downsample layer.

中文翻译：

---

BARS：联合搜索单元拓扑和布局，以获得准确，高效的二进制结构

二进制神经网络（BNN）由于其有希望的效率而受到了广泛关注。当前，大多数BNN研究直接采用广泛使用的CNN架构，这对于BNN可能不是最理想的。本文提出了一种新颖的二进制架构搜索（BARS）流，以在大型设计空间中发现高级二进制架构。具体来说，我们设计了一个针对BNN的两级（Macro \＆Micro）搜索空间，并应用可微的神经体系结构搜索（NAS）来有效地探索该搜索空间。宏级搜索空间包括深度和宽度决策，这是更好地平衡模型性能和容量所必需的。并且，我们还对微观搜索空间进行了修改，以增强BNN的信息流。BNN体系结构搜索的显着挑战在于二进制操作加剧了可区分NAS的“崩溃”问题，并且我们结合了各种搜索和派生策略来稳定搜索过程。在CIFAR-10上，\ method通过$ 2/3 $二进制Ops和$ 1/10 $浮点Ops实现了$ 1.5 \％$的更高精度。在ImageNet上，资源消耗相似，发现\方法的体系结构比手工制作的体系结构可实现$ 3％的精度提高，同时消除了全精度的下采样层。