Neural network architecture design mostly focuses on the new convolutional operator or special topological structure of network block, little attention is drawn to the configuration of stacking each block, called Block Stacking Style (BSS). Recent studies show that BSS may also have an unneglectable impact on networks, thus we design an efficient algorithm to search it automatically. The proposed method, AutoBSS, is a novel AutoML algorithm based on Bayesian optimization by iteratively refining and clustering Block Stacking Style Code (BSSC), which can find optimal BSS in a few trials without biased evaluation. On ImageNet classification task, ResNet50/MobileNetV2/EfficientNet-B0 with our searched BSS achieve 79.29%/74.5%/77.79%, which outperform the original baselines by a large margin. More importantly, experimental results on model compression, object detection and instance segmentation show the strong generalizability of the proposed AutoBSS, and further verify the unneglectable impact of BSS on neural networks.

翻译：神经网络结构设计主要侧重于网络区块的新的革命操作员或特殊地形结构,很少注意每个区块的堆叠配置,称为Block Stacking Style(BS)。最近的研究表明,BSS也可能对网络产生不可分的影响,因此我们设计了一种自动搜索的高效算法。AutoBSS(AutoBSS)是一种新型的Automal 算法,它基于巴伊西亚优化,通过迭接提炼和组合块块堆放风格代码(BSSC),可以在没有偏见评价的少数试验中找到最佳的BSS。关于图像网络分类任务,ResNet50//MobileNetV2/EfficentNet-B0与我们搜索的BSS(BSS)实现79.29%/74.5%/77.79%,大大超过原始基线。更重要的是,关于模型压缩、物体探测和实例分割的实验结果显示,拟议的AutoBSS(BS)具有很强的普遍性,并进一步核实BSS(BSS)对神经网络的不可分化影响。