The linear classifier is widely used in various image classification tasks. It works by optimizing the distance between a sample and its corresponding class center. However, in real-world data, one class can contain several local clusters, e.g., birds of different poses. To address this complexity, we propose a novel multi-center classifier. Different from the vanilla linear classifier, our proposal is established on the assumption that the deep features of the training set follow a Gaussian Mixture distribution. Specifically, we create a conditional Gaussian distribution for each class and then sample multiple sub-centers from that distribution to extend the linear classifier. This approach allows the model to capture intra-class local structures more efficiently. In addition, at test time we set the mean of the conditional Gaussian distribution as the class center of the linear classifier and follow the vanilla linear classifier outputs, thus requiring no additional parameters or computational overhead. Extensive experiments on image classification show that the proposed multi-center classifier is a powerful alternative to widely used linear classifiers. Code available at https://github.com/ZheminZhang1/MultiCenter-Classifier.

翻译：线性分类器广泛应用于各类图像分类任务中，其原理是通过优化样本与其对应类中心之间的距离来实现分类。然而现实数据中，同一类别可能包含多个局部簇群（如不同姿态的鸟类）。为应对这一复杂性，我们提出一种新颖的多中心分类器。与标准线性分类器不同，本方法基于训练集深度特征服从高斯混合分布的假设建立。具体而言，我们为每个类别构建条件高斯分布，并从中采样多个子中心以扩展线性分类器。该策略使模型能更高效地捕获类内局部结构信息。此外，在测试阶段，我们将条件高斯分布的均值设为线性分类器的类中心，并沿用标准线性分类器的输出形式，因此无需引入额外参数或计算开销。大量图像分类实验表明，所提出的多中心分类器可作为广泛使用的线性分类器的强效替代方案。代码开源地址：https://github.com/ZheminZhang1/MultiCenter-Classifier。