论文标题
CLCNET：通过分类置信网络重新思考集成建模
CLCNet: Rethinking of Ensemble Modeling with Classification Confidence Network
论文作者
论文摘要
在本文中，我们提出了一个分类置信网（CLCNET），该网络可以确定分类模型是否正确分类输入样本。它可以以任何维度为单位的向量形式进行分类结果，并将置信度得分作为输出返回，这表示实例正确分类的概率。我们可以在由几个SOTA（最新）分类模型组成的简单级联结构系统中使用CLCNET，我们的实验表明，该系统可以实现以下优点：1。系统可以在推理时自定义平均计算要求（FLOP）。 2。在相同的计算要求下，系统的性能可以超过与系统中模型相同结构的任何模型，但大小不同。实际上，这是一种新型的集合建模。像一般整体建模一样，它可以比单个分类模型获得更高的性能，但是我们的系统所需的计算要比一般集合建模要少得多。我们已将代码上传到GITHUB存储库：https：//github.com/yaoching0/clcnet-rethinking-of-senbleble-modeling。
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.
