Recently,the detection transformer has gained substantial attention for its
inherent minimal post-processing requirement.However,this paradigm relies on
abundant training data,yet in the context of the cross-domain
adaptation,insufficient labels in the target domain exacerbate issues of class
imbalance and model performance degradation.To address these challenges, we
propose a novel class-aware cross domain detection transformer based on the
adversarial learning and mean-teacher framework.First,considering the
inconsistencies between the classification and regression tasks,we introduce an
IoU-aware prediction branch and exploit the consistency of classification and
location scores to filter and reweight pseudo labels.Second, we devise a
dynamic category threshold refinement to adaptively manage model
confidence.Third,to alleviate the class imbalance,an instance-level class-aware
contrastive learning module is presented to encourage the generation of
discriminative features for each class,particularly benefiting minority
classes.Experimental results across diverse domain-adaptive scenarios validate
our method's effectiveness in improving performance and alleviating class
imbalance issues,which outperforms the state-of-the-art transformer based
methods.

我们提出了一种新颖的基于对抗学习和 mean-teacher 框架的类感知跨域检测变换器，通过引入 IoU 感知预测分支、动态类别阈值细化和实例级类感知对比学习模块来解决跨域适应中的标签不足、类不平衡和模型性能下降的问题。实验证明，我们的方法在改善性能和减轻类别不平衡问题方面效果显著优于现有的基于变换器的方法。