让模型在不完整标签下也能准确进行层级图像识别，更贴近真实标注场景。
Free-Grained Hierarchical Visual Recognition
- 允许标签出现在任意层级，模型需从混合粒度数据中学习一致的分类逻辑。
- 在真实标签不完整时，现有方法性能骤降，新方法提升显著。
- 适用于真实世界中标签不统一的图像识别任务，如生态监测、医疗影像等。
层级图像识别旨在沿语义树状结构从大类到细类预测类别标签，传统方法假设每张训练图都完整标注了其整个分类路径。但现实中，远距离鸟图可能只标为“鸟”，而清晰特写则可标为“秃鹰”。我们提出自由粒度训练：标签可在任意层级出现，模型需从不完整、混合粒度的监督信号中学习一致的层级预测。构建了具有不同标签粒度的基准数据集，发现现有层级方法在此设置下性能急剧下降。为弥补缺失监督，提出两种简单方案：一是加入基于文本的宽粒度视觉属性监督；二是将特定层级缺失标签视为半监督学习问题。还研究了自由粒度推理，即模型可自主决定预测深度，在细粒度不确定时返回可靠粗粒度标签。整体任务、数据集与方法使层级识别更贴近真实世界标签生成方式。
原文摘要 · Abstract (English)
Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the tidy assumption that every training image is fully annotated along its taxonomy path. Reality is messier: A distant bird may be labeled only bird, while a clear close-up may justify bald eagle. We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision. We build benchmark datasets with varying label granularity and show that existing hierarchical methods deteriorate sharply in this setting. To make up for missing supervision, we propose two simple solutions: One adds broad text-based supervision that captures visual attributes, and the other treats missing labels at specific taxonomy levels as a semi-supervised learning problem. We also study free-grained inference, where the model chooses how deep to predict, returning a reliable coarse label when a fine-grained one is uncertain. Together, our task, datasets, and methods move hierarchical recognition closer to the way labels arise in the real world.
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。