Timezone: »

Universal Semi-Supervised Learning
Zhuo Huang · Chao Xue · Bo Han · Jian Yang · Chen Gong

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @

Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem where both the class distribution (i.e., class set) and feature distribution (i.e., feature domain) are different between labeled dataset and unlabeled dataset. Such a problem seriously hinders the realistic landing of classical SSL. Different from the existing SSL methods targeting at the open-set problem that only study one certain scenario of class distribution mismatch and ignore the feature distribution mismatch, we consider a more general case where a mismatch exists in both class and feature distribution. In this case, we propose a ''Class-shAring data detection and Feature Adaptation'' (CAFA) framework which requires no prior knowledge of the class relationship between the labeled dataset and unlabeled dataset. Particularly, CAFA utilizes a novel scoring strategy to detect the data in the shared class set. Then, it conducts domain adaptation to fully exploit the value of the detected class-sharing data for better semi-supervised consistency training. Exhaustive experiments on several benchmark datasets show the effectiveness of our method in tackling open-set problems.

Author Information

Zhuo Huang (Nanjing University of Science and Technology)
Chao Xue (JD Explore Academy)
Jian Yang (Nanjing University of Science and Technology)
Chen Gong (Nanjing University of Science and Technology)

More from the Same Authors