arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.06709cs.LGcs.CV
收藏

Top-K Pairwise Ranking:弥合多标签分类中基于排序的评估指标之间的差距

Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification

IIE, Chinese Academy of Sciences(中国科学院自动化研究所);SCS, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院);IIP, ICT, Chinese Academy of Sciences(中国科学院计算技术研究所);SCST, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院);Alibaba Group(阿里巴巴集团);SCST, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区计算机科学与技术学院);BDKM, University of Chinese Academy of Sciences(中国科学院大学大数据与知识管理实验室)

Zitai Wang, Qianqian Xu, Zhiyong Yang, Peisong Wen, Yuan He, Xiaochun Cao, Qingming Huang

AI总结:

针对多标签排序任务中不同评估指标下模型表现不一致的问题,提出兼容现有排序指标的TKPR指标,构建具备理论支撑的代理风险最小化框架,并通过实验验证其有效性。

摘要:

多标签排序会为每个样本返回多个排名靠前的标签,在视觉任务中有着广泛应用。由于其设置复杂,现有研究已提出多种指标来评估模型性能。然而,理论分析和实证观察均表明,同一模型在不同指标上的表现可能不一致。为弥合这一差距,本文提出了一种名为Top-K Pairwise Ranking(TKPR,Top-K成对排序)的新型指标,一系列分析表明TKPR与现有基于排序的指标具有兼容性。基于此,我们进一步构建了TKPR的实证代理风险最小化框架。一方面,该框架采用凸代理损失,具备Fisher一致性的理论支撑;另一方面,我们通过一种名为数据依赖收缩的新技术,为该框架建立了严格的泛化界。最后,在基准数据集上的实证结果验证了所提框架的有效性。

英文摘要:

Multi-label ranking, which returns multiple top-ranked labels for each instance, has a wide range of applications for visual tasks. Due to its complicated setting, prior arts have proposed various measures to evaluate model performances. However, both theoretical analysis and empirical observations show that a model might perform inconsistently on different measures. To bridge this gap, this paper proposes a novel measure named Top-K Pairwise Ranking (TKPR), and a series of analyses show that TKPR is compatible with existing ranking-based measures. In light of this, we further establish an empirical surrogate risk minimization framework for TKPR. On one hand, the proposed framework enjoys convex surrogate losses with the theoretical support of Fisher consistency. On the other hand, we establish a sharp generalization bound for the proposed framework based on a novel technique named data-dependent contraction. Finally, empirical results on benchmark datasets validate the effectiveness of the proposed framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑