用对比学习建模排序关系，提升年龄估计等任务精度
Contrastive Order Learning: A General Framework for Ordinal Regression
- 通过样本间排名差异设计软权重对比损失，精细建模排序关系
- 在人脸年龄、图像/视频质量评估上均达当前最优表现
- 适合需要精确排序建模的多领域回归任务
我们提出对比排序学习（ConOrd），一种结合对比学习与排序学习优势的新型排序回归框架。对比学习虽能利用批量内所有样本，却通常忽略标签的内在顺序；而排序学习虽显式建模标签序关系，但常依赖局部边际比较，难以捕捉全局排序结构。ConOrd通过引入基于排名差的软亲和与差异权重的对比排序损失，实现对批量内所有样本对之间排序关系的细粒度建模。在人脸年龄估计、盲图像质量评估及盲视频质量评估等多种排序回归任务上的大量实验表明，ConOrd在不同场景下均持续取得当前最优性能且具有良好泛化能力。源代码已公开于 https://github.com/cwlee00/ConOrd。
原文摘要 · Abstract (English)
We propose contrastive order learning (ConOrd), a contrastive learning framework for ordinal regression that integrates the strengths of contrastive learning and order learning. While contrastive learning effectively leverages all samples in a batch, it typically ignores the inherent ordering among rank labels. Conversely, order learning explicitly models label ordinality but often relies on local, margin-based comparisons, limiting its ability to capture global ordinal structure. ConOrd addresses these limitations by introducing a contrastive order loss with soft affinity and disparity weights based on rank differences, enabling fine-grained modeling of ordinal relationships across all sample pairs within a batch. Extensive experiments on a range of ordinal regression tasks, including facial age estimation, blind image quality assessment, and blind video quality assessment, demonstrate that ConOrd consistently achieves state-of-the-art performance and generalizes well across diverse ordinal regression scenarios. The source code is available at https://github.com/cwlee00/ConOrd.
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。