Credible Teacher for Semi-Supervised Object Detection in Open Scene
This addresses a specific challenge in semi-supervised object detection for computer vision applications, but appears incremental as it builds on existing self-training approaches.
The paper tackles the problem of unknown objects in unlabeled data increasing uncertainty for known objects in Open Scene Semi-Supervised Object Detection, proposing Credible Teacher to reduce this uncertainty and improve performance, with empirical results showing it significantly outperforms existing methods.
Semi-Supervised Object Detection (SSOD) has achieved resounding success by leveraging unlabeled data to improve detection performance. However, in Open Scene Semi-Supervised Object Detection (O-SSOD), unlabeled data may contains unknown objects not observed in the labeled data, which will increase uncertainty in the model's predictions for known objects. It is detrimental to the current methods that mainly rely on self-training, as more uncertainty leads to the lower localization and classification precision of pseudo labels. To this end, we propose Credible Teacher, an end-to-end framework. Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels. Empirical results have demonstrated our method effectively restrains the adverse effect caused by O-SSOD and significantly outperforms existing counterparts.