We propose Equiangular Basis Vectors (EBVs) for classification tasks. In deep neural networks, models usually end with a k-way fully connected layer with softmax to handle different classification tasks. The learning objective of these methods can be summarized as mapping the learned feature representations to the samples' label space. While in metric learning approaches, the main objective is to learn a transformation function that maps training data points from the original space to a new space where similar points are closer while dissimilar points become farther apart. Different from previous methods, our EBVs generate normalized vector embeddings as "predefined classifiers" which are required to not only be with the equal status between each other, but also be as orthogonal as possible. By minimizing the spherical distance of the embedding of an input between its categorical EBV in training, the predictions can be obtained by identifying the categorical EBV with the smallest distance during inference. Various experiments on the ImageNet-1K dataset and other downstream tasks demonstrate that our method outperforms the general fully connected classifier while it does not introduce huge additional computation compared with classical metric learning methods. Our EBVs won the first place in the 2022 DIGIX Global AI Challenge, and our code is open-source and available at https://github.com/NJUST-VIPGroup/Equiangular-Basis-Vectors.

翻译：我们提出用于分类任务的等角基向量（Equiangular Basis Vectors, EBVs）。在深度神经网络中，模型通常以k路全连接层配合softmax函数处理不同分类任务，其学习目标可概括为将学习到的特征表示映射至样本的标签空间。而度量学习方法的主要目标是学习一个变换函数，将训练数据点从原始空间映射至新空间，使得相似点更接近、不相似点更疏远。与先前方法不同，我们的EBVs生成归一化向量嵌入作为"预定义分类器"，这些嵌入不仅需要彼此地位平等，还需尽可能正交。通过训练过程中最小化输入嵌入与其对应类别EBV间的球面距离，推理时可通过识别距离最小的类别EBV获得预测结果。在ImageNet-1K数据集及其他下游任务上的实验表明，我们的方法优于通用全连接分类器，同时相比经典度量学习方法未引入大量额外计算。我们的EBVs在2022年DIGIX全球AI挑战赛中荣获第一名，代码已开源并发布于https://github.com/NJUST-VIPGroup/Equiangular-Basis-Vectors。