用局部特征提升图像等级回归精度，解决标签模糊问题
Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression
- 引入局部区域标签筛选与引导机制，挖掘图像级标签中的细粒度信息
- 设计双层模糊学习模块，从局部和通道两个维度处理标签不确定性
- 在多个数据集上显著优于现有方法，尤其擅长区分难分类样本
等级回归将回归与分类相结合，将对象分配到有序类别中。尽管人类专家依赖判别性局部区域特征进行判断，但当前方法受限于仅有图像级等级标签，忽略了细粒度的局部特征。本文提出一种双层模糊学习与局部引导框架（DFPG），从模糊等级标签中学习精确的基于特征的分级边界，并引入局部监督。具体而言，我们设计了局部标签生成与过滤策略，使模型仅用图像级标签即可聚焦局部特征。进一步地，构建双层模糊学习模块，利用模糊逻辑从局部和通道两个层面量化并处理标签模糊性。在多个图像等级回归数据集上的大量实验表明，所提方法具有显著优势，尤其在区分难以分类的样本方面表现突出。代码已开源：https://github.com/ZJUMAI/DFPG-ord。
原文摘要 · Abstract (English)
Ordinal regression bridges regression and classification by assigning objects to ordered classes. While human experts rely on discriminative patch-level features for decisions, current approaches are limited by the availability of only image-level ordinal labels, overlooking fine-grained patch-level characteristics. In this paper, we propose a Dual-level Fuzzy Learning with Patch Guidance framework, named DFPG that learns precise feature-based grading boundaries from ambiguous ordinal labels, with patch-level supervision. Specifically, we propose patch-labeling and filtering strategies to enable the model to focus on patch-level features exclusively with only image-level ordinal labels available. We further design a dual-level fuzzy learning module, which leverages fuzzy logic to quantitatively capture and handle label ambiguity from both patch-wise and channel-wise perspectives. Extensive experiments on various image ordinal regression datasets demonstrate the superiority of our proposed method, further confirming its ability in distinguishing samples from difficult-to-classify categories. The code is available at https://github.com/ZJUMAI/DFPG-ord.
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。