arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.01468cs.CVcs.AI
收藏

面向长尾学习的决策边界感知生成

Decision Boundary-aware Generation for Long-tailed Learning

Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China(中国教育部多媒体可信感知与高效计算重点实验室);Xiamen University(厦门大学);College of Computer Science and Software Engineering(计算机科学与软件工程学院);Shenzhen University(深圳大学);Department of Statistical Science(统计科学系);University College London(伦敦大学学院);Division of Arts and Machine Creativity(艺术与机器创造力 division);Hong Kong University of Science and Technology(香港科技大学)

Jiacheng Yang, Ruichi Zhang, Chikai Shang, Mengke Li, Xinyi Shang, Junlong Gao, Yonggang Zhang, Yang Lu

AI总结:

本文提出DBG框架,通过生成边界附近样本提升表示学习,缓解长尾数据分布不均问题,提升尾类和整体准确率。

摘要:

长尾数据使决策边界偏向头部类别并降低尾部类别精度。基于扩散的生成增强方法通过生成额外数据缓解此问题,而头到尾迁移进一步减轻长尾数据集继承的生成偏差。然而,本文发现头到尾迁移虽然有助于平衡分类器的决策空间,但也会引起潜在的非局部特征混合,导致类别间特征纠缠、决策边界重叠和尾部类别分布偏移。为此,本文首先识别边界模糊问题,提出决策边界感知生成(DBG)框架,通过生成具有信息量的边界附近样本促进近边界表示学习。整体而言,DBG在重平衡长尾数据集的同时,为长尾学习提供更可分的决策空间。在标准长尾基准上,DBG在提升尾部类别和整体准确率方面表现一致,且减少类别间重叠。DBG的代码可在https://github.com/keepdigitalabc-svg/DBG获取。

英文摘要:

Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional data, while head-to-tail transfer further mitigate the generator bias inherit from long-tailed dataset. However, we show that while head-to-tail transfer helps balance the decision space of the classifier, it also induces latent non-local feature mixing that entangles inter-class features, causing decision boundary overlap and tail class distribution shift. To address this, we first identify the problem of boundary ambiguity and then propose Decision Boundary-aware Generation (DBG) framework, which promotes near-boundary representation learning by generating informative near-boundary samples. Overall, DBG rebalances the long-tailed dataset while yielding more separable decision space for long-tailed learning. Across standard long-tailed benchmarks, DBG consistently improves tail class and overall accuracy with less inter-class overlap. The code of DBG is available at https://github.com/keepdigitalabc-svg/DBG.

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。

↑