论文标题
Autobss：用于块堆叠样式搜索的有效算法
AutoBSS: An Efficient Algorithm for Block Stacking Style Search
论文作者
论文摘要
神经网络体系结构设计主要集中在新的卷积操作员或网络块的特殊拓扑结构上，几乎没有关注堆叠每个块的配置，称为块堆叠样式（BSS）。最近的研究表明，BSS也可能对网络产生不可销的影响，因此我们设计了一种有效的算法来自动搜索它。所提出的方法AutoBSS是一种新型的自动算法，基于贝叶斯优化，通过迭代精炼和聚类块堆叠样式代码（BSSC），可以在几个试验中找到最佳的BSS，而无需评估。在ImageNet分类任务上，使用我们搜索的BSS的RESNET50/MOBILENETV2/EFIDEDNET-B0实现79.29％/74.5％/77.79％，这比原始基线的优于原始基线的幅度很大。更重要的是，对模型压缩，对象检测和实例分割的实验结果表明，提出的AutoBss的强烈概括性，并进一步验证BSS对神经网络的不可限制的影响。
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.
