Exploring dense connectivity of convolutional operators establishes critical "synapses" to communicate feature vectors from different levels and enriches the set of transformations on Computer Vision applications. Yet, even with heavy-machinery approaches such as Neural Architecture Search (NAS), discovering effective connectivity patterns requires tremendous efforts due to either constrained connectivity design space or a sub-optimal exploration process induced by an unconstrained search space. In this paper, we propose CSCO, a novel paradigm that fabricates effective connectivity of convolutional operators with minimal utilization of existing design motifs and further utilizes the discovered wiring to construct high-performing ConvNets. CSCO guides the exploration via a neural predictor as a surrogate of the ground-truth performance. We introduce Graph Isomorphism as data augmentation to improve sample efficiency and propose a Metropolis-Hastings Evolutionary Search (MH-ES) to evade locally optimal architectures and advance search quality. Results on ImageNet show ~0.6% performance improvement over hand-crafted and NAS-crafted dense connectivity. Our code is publicly available.

翻译：探索卷积算子的密集连通性为计算机视觉应用中不同层级的特征向量通信建立了关键“突触”，并丰富了变换集合。然而，即便采用神经架构搜索（NAS）等重型方法，由于连通性设计空间受限或非约束搜索空间导致的次优探索过程，发现有效的连通性模式仍需要巨大努力。本文提出CSCO这一新型范式，以最小化对现有设计模式的依赖来构建卷积算子的有效连通性，并进一步利用所发现的连接构造高性能卷积网络。CSCO通过神经预测器作为真实性能的代理来引导探索。我们引入图同构作为数据增强手段以提高样本效率，并提出梅特罗波利斯-黑斯廷斯进化搜索（MH-ES）以避免局部最优架构并提升搜索质量。在ImageNet上的结果表明，与手工设计及NAS设计的密集连通性相比，性能提升约0.6%。我们的代码已公开。