Recent work on efficient neural network architectures focuses on discovering a solitary network that can achieve superior computational efficiency and accuracy. While this paradigm has yielded impressive results, the search for novel architectures usually requires significant computational resources. In this work, we demonstrate a simple complementary paradigm to obtain efficient and accurate models that requires no architectural tuning. We show that committee-based models, i.e., ensembles or cascades of models, can easily obtain higher accuracy with less computation when compared to a single model. We extensively investigate the benefits of committee-based models on various vision tasks and architecture families. Our results suggest that in the large computation regime, model ensembles are a more cost-effective way to improve accuracy than using a large solitary model. We also find that the computational cost of an ensemble can be significantly reduced by converting them to cascades, while often retaining the original accuracy of the full ensemble.

本文研究委员会模型的效率，揭示即使使用最简单的基于现有预训练模型构建委员会的方法，依然可以在图像分类、视频分类和语义分割等任务中达到与现有最先进模型相当或更高的精度，且速度更快，比如EfficientNet级联可以达到超过B7 5.4倍的加速。

委员会的智慧：一个被忽视的更快更准的模型方法