通过分层剪枝加速扩散分类器，提升推理速度。
Just Leaf It: Accelerating Diffusion Classifiers with Hierarchical Class Pruning
- 利用标签层级结构剪枝无关高层类别，只在相关子类评估。
- 推理速度最高提升60%，准确率保持甚至提高。
- 适合需要快速分类的大型应用，可调节速度与精度平衡。
扩散模型凭借其生成能力在图像分类任务中表现出色，基于贝叶斯定理实现。然而，现有扩散分类器需对每个输入评估所有标签候选，导致计算成本高，难以用于大规模应用。为此，我们提出分层扩散分类器（HDC），利用数据集中存在的层级标签结构或明确的父子关系，剪除无关的高层类别，并仅在相关子类别（叶节点及子树）内进行精细化预测，从而减少总分类评估次数。实验表明，该方法可使推理速度最高提升60%，同时保持甚至提升分类准确率。本工作为速度与精度之间提供了可调控制机制，使基于扩散模型的分类更适用于大规模场景。
原文摘要 · Abstract (English)
Diffusion models, celebrated for their generative capabilities, have recently demonstrated surprising effectiveness in image classification tasks by using Bayes' theorem. Yet, current diffusion classifiers must evaluate every label candidate for each input, creating high computational costs that impede their use in large-scale applications. To address this limitation, we propose a Hierarchical Diffusion Classifier (HDC) that exploits hierarchical label structures or well-defined parent-child relationships in the dataset. By pruning irrelevant high-level categories and refining predictions only within relevant subcategories (leaf nodes and sub-trees), HDC reduces the total number of class evaluations. As a result, HDC can speed up inference by as much as 60% while preserving and sometimes even improving classification accuracy. In summary, our work provides a tunable control mechanism between speed and precision, making diffusion-based classification more feasible for large-scale applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。