论文标题
小组合奏：在单个Convnet中学习convnet的合奏
Group Ensemble: Learning an Ensemble of ConvNets in a single ConvNet
论文作者
论文摘要
合奏学习是提高机器学习准确性的一般技术。但是，Convnets合奏的大量计算限制了其在深度学习中的用法。在本文中，我们介绍了小组集合网络（Genet），这是一种结构在单个Convnet中的架构。通过共享基础和多头结构，基因被分为几个组，以使单个转变中的显式集合学习成为可能。由于组卷积和共享基础，基因可以充分利用显式集合学习的优势，同时保留与单个Convnet相同的计算。此外，我们将小组平均，小组摇摆和群体提升为汇总这些合奏成员的三种不同策略。最后，基因的表现优于较大的单个网络，较小网络的标准集合以及其他有关CIFAR和Imagenet的最新方法。具体而言，对于ImageNet上的Resnext-50，组集合将TOP-1误差降低了1.83％。我们还证明了其对动作识别和对象检测任务的有效性。
Ensemble learning is a general technique to improve accuracy in machine learning. However, the heavy computation of a ConvNets ensemble limits its usage in deep learning. In this paper, we present Group Ensemble Network (GENet), an architecture incorporating an ensemble of ConvNets in a single ConvNet. Through a shared-base and multi-head structure, GENet is divided into several groups to make explicit ensemble learning possible in a single ConvNet. Owing to group convolution and the shared-base, GENet can fully leverage the advantage of explicit ensemble learning while retaining the same computation as a single ConvNet. Additionally, we present Group Averaging, Group Wagging and Group Boosting as three different strategies to aggregate these ensemble members. Finally, GENet outperforms larger single networks, standard ensembles of smaller networks, and other recent state-of-the-art methods on CIFAR and ImageNet. Specifically, group ensemble reduces the top-1 error by 1.83% for ResNeXt-50 on ImageNet. We also demonstrate its effectiveness on action recognition and object detection tasks.
