SAFER-STUDENT for Safe Deep Semi-Supervised Learning With Unseen-Class Unlabeled Data

Abstract

Deep semi-supervised learning (SSL) methods aim to utilize abundant unlabeled data to improve the seen-class classification. However, in the open-world scenario, collected unlabeled data tend to contain unseen-class data, which would degrade the generalization to seen-class classification. Formally, we define the problem as safe deep semi-supervised learning with unseen-class unlabeled data. One intuitive solution is removing these unseen-class instances after detecting them during the SSL process. Nevertheless, the performance of unseen-class identification is limited by the lack of suitable score function, the uncalibrated model, and the small number of labeled data. To this end, we propose a safe SSL method called SAFE <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b> -STUDENT from the teacher-student view. Firstly, to enhance the ability of teacher model to identify seen and unseen classes, we propose a general scoring framework called <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</u> iscrepancy with <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</u> aw (DR). Secondly, based on unseen-class data mined by teacher model from unlabeled data, we calibrate student model by newly proposed <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U</u> nseen-class <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</u> nergy-bounded <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</u> alibration (UEC) loss. Thirdly, based on seen-class data mined by teacher model from unlabeled data, we propose <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">W</u> eighted <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</u> onfirmation <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</u> ias <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</u> limination (WCBE) loss to boost seen-class classification of student model. Extensive studies show that SAFE <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b> -STUDENT remarkably outperforms the state-of-the-art, verifying the effectiveness of our method in the under-explored problem.