In this paper, we propose a Classification Confidence Network (CLCNet) that can determine whether the classification model classifies input samples correctly. It can take a classification result in the form of vector in any dimension, and return a confidence score as output, which represents the probability of an instance being classified correctly. We can utilize CLCNet in a simple cascade structure system consisting of several SOTA (state-of-the-art) classification models, and our experiments show that the system can achieve the following advantages: 1. The system can customize the average computation requirement (FLOPs) per image while inference. 2. Under the same computation requirement, the performance of the system can exceed any model that has identical structure with the model in the system, but different in size. In fact, this is a new type of ensemble modeling. Like general ensemble modeling, it can achieve higher performance than single classification model, yet our system requires much less computation than general ensemble modeling. We have uploaded our code to a github repository: https://github.com/yaoching0/CLCNet-Rethinking-of-Ensemble-Modeling.
翻译:在本文中,我们提出一个分类信任网络(CLCNet),它可以确定分类模型是否正确分类输入样本。它可以以任何层面的矢量形式进行分类,并将信任分数作为输出返回,这代表了正确分类的概率。我们可以在一个简单的级联结构系统中使用CLCNet,这个系统由若干SOTA(最先进的)分类模型组成,我们的实验表明,这个系统可以实现以下优点:1. 该系统可以在推断时定制每个图像的平均计算要求(FLOPs)。2. 在同一计算要求下,该系统的性能可以超过与系统中的模型结构相同但规模不同的任何模型。事实上,这是一种新型的共性模型。与通用模型一样,它可以达到比单一的分类模型更高的性能,但我们的系统比普通的模块要少得多的计算。我们已经将我们的代码上传到一个Github存储库: https://github.com/yaoch0/CLE-Revonging-Amble-Annex-Emble-Emble-Emble-Emble-Emble-Emblementing)。