In this paper, we aim to improve the performance of a deep learning model towards image classification tasks, proposing a novel anchor-based training methodology, named \textit{Online Anchor-based Training} (OAT). The OAT method, guided by the insights provided in the anchor-based object detection methodologies, instead of learning directly the class labels, proposes to train a model to learn percentage changes of the class labels with respect to defined anchors. We define as anchors the batch centers at the output of the model. Then, during the test phase, the predictions are converted back to the original class label space, and the performance is evaluated. The effectiveness of the OAT method is validated on four datasets.

翻译：本文旨在提升深度学习模型在图像分类任务中的性能，提出了一种新颖的基于锚点的训练方法，称为“在线锚点训练”。该方法受基于锚点的目标检测方法的启发，不直接学习类别标签，而是训练模型学习类别标签相对于预设锚点的百分比变化。我们将模型输出层的批次中心定义为锚点。在测试阶段，预测结果被转换回原始类别标签空间并进行性能评估。OAT方法的有效性在四个数据集上得到了验证。