Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches mainly focus on either of these two difficulties, even though they are closely coupled in cross domain object detection. To solve this problem, we propose a novel Target-perceived Dual-branch Distillation (TDD) framework. By integrating detection branches of both source and target domains in a unified teacher-student learning scheme, it can reduce domain shift and generate reliable supervision effectively. In particular, we first introduce a distinct Target Proposal Perceiver between two domains. It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention. Afterwards, we design a concise Dual Branch Self Distillation strategy for model training, which can progressively integrate complementary object knowledge from different domains via self-distillation in two branches. Finally, we conduct extensive experiments on a number of widely-used scenarios in cross domain object detection. The results show that our TDD significantly outperforms the state-of-the-art methods on all the benchmarks. Our code and model will be available at https://github.com/Feobi1999/TDD.
翻译:在野外,跨域物体探测是一项现实和具有挑战性的任务。由于数据分布的大规模转移和在目标领域缺乏实例性说明,它受到性能退化的影响。现有的方法主要侧重于这两个难题中的任何一个,尽管它们在跨域物体探测中相互密切结合。为了解决这个问题,我们提出了一个新的新型的目标-渗透双部门蒸馏(TDD)框架。通过将源和目标领域的探测分支纳入统一的教师-学生学习计划,它能够减少域转移,并有效地产生可靠的监督。特别是,我们首先在两个领域之间引入了独特的目标建议 Perceiver。它能够适应性地加强源探测器,通过利用迭代交叉注意的目标提议环境来在目标图像中看到对象。随后,我们为示范培训设计了一个简明的双部门自我蒸馏(D)战略,通过在两个分支的自我蒸馏,逐步将不同领域的补充对象知识整合在一起。最后,我们就跨域物体探测中广泛使用的情景进行了广泛的实验。结果显示,我们的TDD明显超越了在1999年/F中现有的标准。我们的数据-TD/F标准将大大超越了我们现有的标准。