cs.AI updates on arXiv.org 07月03日 12:07
Distribution Matching for Self-Supervised Transfer Learning
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一种名为DM的自监督迁移学习方法,通过驱动表示分布趋向预定义的参考分布,同时保持增强不变性,实现直观结构化的学习表示空间,实验结果表明DM在目标分类任务上表现优异,并提供理论保障。

arXiv:2502.14424v2 Announce Type: replace-cross Abstract: In this paper, we propose a novel self-supervised transfer learning method called \underline{\textbf{D}}istribution \underline{\textbf{M}}atching (DM), which drives the representation distribution toward a predefined reference distribution while preserving augmentation invariance. DM results in a learned representation space that is intuitively structured and therefore easy to interpret. Experimental results across multiple real-world datasets and evaluation metrics demonstrate that DM performs competitively on target classification tasks compared to existing self-supervised transfer learning methods. Additionally, we provide robust theoretical guarantees for DM, including a population theorem and an end-to-end sample theorem. The population theorem bridges the gap between the self-supervised learning task and target classification accuracy, while the sample theorem shows that, even with a limited number of samples from the target domain, DM can deliver exceptional classification performance, provided the unlabeled sample size is sufficiently large.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

自监督学习 迁移学习 DM方法 分类性能 理论保障
相关文章