This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task. Different from prior HIC methods, our hierarchical prompting is the first to explicitly inject ancestor-class information as a tokenized hint that benefits the descendant-class discrimination. We think it well imitates human visual recognition, i.e., humans may use the ancestor class as a prompt to draw focus on the subtle differences among descendant classes. We model this prompting mechanism into a Transformer with Hierarchical Prompting (TransHP). TransHP consists of three steps: 1) learning a set of prompt tokens to represent the coarse (ancestor) classes, 2) on-the-fly predicting the coarse class of the input image at an intermediate block, and 3) injecting the prompt token of the predicted coarse class into the intermediate feature. Though the parameters of TransHP maintain the same for all input images, the injected coarse-class prompt conditions (modifies) the subsequent feature extraction and encourages a dynamic focus on relatively subtle differences among the descendant classes. Extensive experiments show that TransHP improves image classification on accuracy (e.g., improving ViT-B/16 by +2.83% ImageNet classification accuracy), training data efficiency (e.g., +12.69% improvement under 10% ImageNet training data), and model explainability. Moreover, TransHP also performs favorably against prior HIC methods, showing that TransHP well exploits the hierarchical information.

翻译：本文探索了一种用于层级图像分类（HIC）任务的层级提示机制。与现有HIC方法不同，我们的层级提示首次将祖先类信息显式注入为标记化提示，以促进子类判别。我们认为该方法很好地模仿了人类视觉识别过程——即人类可能利用祖先类作为提示，聚焦子类间的细微差异。我们将该提示机制建模为层级提示变压器（TransHP）。TransHP包含三个步骤：1）学习一组提示标记以表征粗粒度（祖先）类别；2）在中间模块实时预测输入图像的粗粒度类别；3）将预测粗粒度类别的提示标记注入中间特征。尽管TransHP对所有输入图像保持相同参数，但注入的粗粒度类别提示条件（修改）了后续特征提取过程，从而动态聚焦子类间的相对细微差异。大量实验表明，TransHP在分类精度（例如，在ImageNet分类任务中使ViT-B/16提升+2.83%）、训练数据效率（例如，仅使用10% ImageNet训练数据时提升+12.69%）及模型可解释性方面均有显著改进。此外，TransHP相较现有HIC方法也展现出更优性能，证明其能有效利用层级信息。