arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.27596cs.CV
收藏

SECOS:面向开放世界半监督学习的语义捕获用于严格分类

SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning

Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University(中国教育部多媒体可信感知与高效计算重点实验室,厦门大学);College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机科学与软件工程学院);School of Computer Science and Technology, Guangdong University of Technology(广东工业大学计算机科学与技术学院);School of Computer Science, University of Nottingham(诺丁汉大学计算机科学学院)

Hezhao Liu, Jiacheng Yang, Junlong Gao, Mengke Li, Yiqun Zhang, Shreyank N Gowda, Yang Lu

AI总结:

SECOS通过外部知识提取并对齐多模态语义表示,为新类别提供显式监督信号,提升开放世界半监督学习中的分类性能。

摘要:

在开放世界半监督学习(OWSSL)中,模型从带标签数据和包含已知和新类别的未带标签数据中学习。现有OWSSL方法无法实现严格分类,因为新样本在训练中缺乏显式监督,且缺乏提取潜在语义信息的机制,导致预测标签与候选文本标签无语义对应。为解决此问题,我们引入SEmantic Capture for Open-world Semi-supervised learning(SECOS),直接从候选集预测文本标签,满足实际OWSSL应用需求。SECOS利用外部知识提取并对齐已知和新类别的多模态语义表示,为新类别提供显式监督信号。大量实验表明,即使在更宽松的后处理匹配设置下评估,SECOS仍能比现有方法高出高达5.4%,凸显其优越性。代码可在https://github.com/ganchi-huanggua/OSSL-Classification获取。

英文摘要:

In open-world semi-supervised learning (OWSSL), a model learns from labeled data and unlabeled data containing both known and novel classes. In practical OWSSL applications, models are expected to perform rigorous classification by directly selecting the most semantically relevant label from a candidate set for each sample. Existing OWSSL methods fail to achieve this because novel samples are trained without explicit supervision, and these methods lack mechanisms to extract latent semantic information, resulting in predicted labels that have no semantic correspondence to candidate textual labels. To address this, we introduce SEmantic Capture for Open-world Semi-supervised learning (SECOS), which directly predicts textual labels from the candidate set without post-processing, meeting the requirements of practical OWSSL applications. SECOS leverages external knowledge to extract and align semantic representations across modalities for both known and novel classes, providing explicit supervisory signals for training novel classes. Extensive experiments demonstrate that even when existing OWSSL methods are evaluated under the more lenient post-hoc matching setting, SECOS still surpasses them by up to 5.4\% without such assistance, highlighting its superior effectiveness. Code is available at https://github.com/ganchi-huanggua/OSSL-Classification.

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。

↑