# Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting Source: [Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:23:36.215Z Authors: Hao Liu, Bin Chen, Bo Wang, Chunpeng Wu, Feng Dai, Peng Wu Published: 2022-07-12T06:16:48.000Z ## Abstract Recently, many semi-supervised object detection (SSOD) methods adopt teacher-student framework and have achieved state-of-the-art results. However, the teacher network is tightly coupled with the student network since the teacher is an exponential moving average (EMA) of the student, which causes a performance bottleneck. To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2. Based on these networks, a cycle self-training mechanism is built, i.e., S1${\\rightarrow}$T1${\\rightarrow}$S2${\\rightarrow}$T2${\\rightarrow}$S1. For S${\\rightarrow}$T, we also utilize the EMA weights of the students to update the teachers. For T${\\rightarrow}$S, instead of providing supervision for its own student S1(S2) directly, the teacher T1(T2) generates pseudo-labels for the student S2(S1), which looses the coupling effect. Moreover, owing to the property of EMA, the teacher is most likely to accumulate the biases from the student and make the mistakes irreversible. To mitigate the problem, we also propose a distribution consistency reweighting strategy, where pseudo-labels are reweighted based on distribution consistency across the teachers T1 and T2. With the strategy, the two students S2 and S1 can be trained robustly with noisy pseudo labels to avoid confirmation biases. Extensive experiments prove the superiority of CST by consistently improving the AP over the baseline and outperforming state-of-the-art methods by 2.1% absolute AP improvements with scarce labeled data. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on MS-COCO 2017 (val)](): Object Detection; MS-COCO 2017 (val); mAP: 43.3. - [Object Detection on PASCAL VOC 2007 (test)](): Object Detection; PASCAL VOC 2007 (test); mAP: 53.5. ## Original sources and implementation [Original paper]() [PDF]()