Open-set semi-supervised object detection (OSSOD) leverages practical open-set unlabeled datasets with out-of-distribution (OOD) instances for semi-supervised object detection (SSOD). The main challenge in OSSOD is distinguishing and filtering the OOD instances (i.e., outliers) from in-distribution (ID) instances during pseudo-labeling. The only OSSOD work employs an additional offline OOD detection network trained solely with labeled data for solving this problem. However, the limited training data restricts the potential for improvement. Meanwhile, the offline strategy results in low efficiency. To alleviate these issues, this paper proposes an end-to-end online OSSOD framework that improves performance and efficiency: 1) We propose a semi-supervised outlier filtering method that more effectively filters the OOD instances by using both labeled and unlabeled data. 2) We propose a threshold-free Dual Competing OOD head that further improves the performance by suppressing the mispredictions during semi-supervised outlier filtering. 3) Our proposed method is an online end-to-end trainable OSSOD framework. Experimental results show that our method achieves state-of-the-art performance on several OSSOD benchmarks compared to existing methods. Moreover, additional experiments show that our method can be easily applied to different SSOD frameworks.

翻译：暂无翻译