arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.01649cs.LGcs.AI
收藏

无源跨域持续学习

Source-Free Cross-Domain Continual Learning

STEM, University of South Australia(南澳大利亚大学STEM学院);Faculty of Electrical and Computer Engineering, University of Ljubljana(卢布尔雅那大学电气与计算机工程学院)

Muhammad Tanzil Furqon, Mahardhika Pratama, Igor Škrjanc, Lin Liu, Habibullah Habibullah, Kutluyil Dogancay

AI总结:

针对隐私受限下无源标注数据的跨域持续学习难题,提出融合源预训练模型与大视觉语言模型的REFEREE方法,通过频率感知提示、不确定性加权和KLDA解决域偏移、噪声伪标签与灾难性遗忘,性能超越有源数据的现有方法。

摘要:

尽管现有的跨域持续学习方法已成功解决了许多存在域偏移的流式任务,但它们需要完全标注的源域数据,这限制了其在隐私受限环境中的可行性。本文进一步研究了完全禁止使用源域样本的无源跨域持续学习问题。\n我们提出了无排练的频率感知动态提示协作(REFEREE)思路,以解决跨域持续学习场景中缺少标注源域样本的问题。REFEREE 基于源预训练模型与大规模视觉-语言模型的协同构建,从而克服了仅依赖源预训练模型时泛化效果次优的问题。\n源域与目标域之间的域偏移问题通过频率感知提示技术处理,该技术鼓励低频分量同时抑制高频分量。这一策略生成的频率感知增强样本对噪声伪标签具有鲁棒性。噪声伪标签问题通过不确定性感知加权策略进一步解决:均值和协方差矩阵根据预测不确定性进行加权,从而减轻噪声伪标签的负面影响。此外,灾难性遗忘(CF)问题通过核线性判别分析(KLDA)克服:主干网络被冻结,同时使用由随机核方法引导的线性判别分析方法执行分类。\n我们严格的数值研究证实了所提方法的优势:它以显著的幅度优于能够访问源域样本的现有技术。

英文摘要:

Although existing cross-domain continual learning approaches successfully address many streaming tasks having domain shifts, they call for a fully labeled source domain hindering their feasibility in the privacy constrained environments. This paper goes one step ahead with the problem of source-free cross-domain continual learning where the use of source-domain samples are completely prohibited. We propose the idea of rehearsal-free frequency-aware dynamic prompt collaborations (REFEREE) to cope with the absence of labeled source-domain samples in realm of cross-domain continual learning. REFEREE is built upon a synergy between a source-pre-trained model and a large-scale vision-language model, thus overcoming the problem of sub-optimal generalizations when relying only on a source pre-trained model. The domain shift problem between the source domain and the target domain is handled by a frequency-aware prompting technique encouraging low-frequency components while suppressing high-frequency components. This strategy generates frequency-aware augmented samples, robust against noisy pseudo labels. The noisy pseudo-label problem is further addressed with the uncertainty-aware weighting strategy where the mean and covariance matrix are weighted by prediction uncertainties, thus mitigating the adverse effects of the noisy pseudo label. Besides, the issue of catastrophic forgetting (CF) is overcome by kernel linear discriminant analysis (KLDA) where the backbone network is frozen while the classification is performed using the linear discriminant analysis approach guided by the random kernel method. Our rigorous numerical studies confirm the advantage of our approach where it beats prior arts having access to source domain samples with significant margins.

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。

↑