SECOS：面向开放世界半监督学习中严格分类的语义捕获
SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning
用外部视觉-语言知识为无标注新类样本构造显式语义监督，把开放世界半监督分类从'聚类后匹配'变成直接输出候选文本标签，可迁移到开放词表识别与新类发现场景。
原文依据 SECOS leverages external knowledge to extract and align semantic representations across modalities for both known and novel classes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在开放世界半监督学习（OWSSL）中，模型从标注数据以及同时包含已知类与新颖类的无标注数据中学习。在实际的 OWSSL 应用中，模型需要执行严格分类，即对每个样本直接从候选集中选出语义上最相关的标签。现有 OWSSL 方法无法做到这一点，因为新颖样本是在缺乏显式监督的情况下训练的，且这些方法缺少提取潜变量语义信息的机制，导致预测标签与候选文本标签之间不存在语义对应关系。为解决该问题，我们提出面向开放世界半监督学习的语义捕获方法（SECOS），它无需后处理即可直接从候选集中预测文本标签，满足实际 OWSSL 应用的要求。SECOS 借助外部知识，为已知类与新颖类提取并对齐跨模态的语义表征，从而为新颖类的训练提供显式监督信号。大量实验表明，即便现有 OWSSL 方法在更宽松的事后匹配设定下进行评估，SECOS 在没有此类辅助的情况下仍以最高 5.4% 的优势超越它们，凸显了其更优的有效性。代码见 https://github.com/ganchi-huanggua/OSSL-Classification。
英文原文摘要 1364 字符
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.