通过原型增强提升特征紧凑性，显著缓解跨域目标检测的分布差异。
PACF: Prototype Augmented Compact Features for Improving Domain Adaptive Object Detection
- 引入原型交叉熵损失，约束目标域特征的类内分布。
- 设计互正则化机制，使线性与原型分类器协同优化特征紧凑性。
- 在多个迁移设置下性能领先，适合跨域检测场景应用。
近年来目标检测技术发展迅速，但将现成检测器应用于新领域时性能显著下降，主要源于域间差异。现有检测器在目标域中表现出比源域更高的类条件特征方差及均值偏移。为此，本文提出原型增强紧凑特征（PACF）框架，以规整类内特征分布。我们对目标域特征相关似然的下界进行了深入理论分析，推导出原型交叉熵损失，进一步校准目标域RoI特征的分布。此外，设计了互正则化策略，使线性分类器与原型分类器相互学习，既促进特征紧凑性，又提升可区分性。得益于该框架，目标域特征的类条件分布方差显著降低，域间类均值偏移也进一步减少。在多种迁移设置下的实验结果达到当前最优水平，验证了方法的广泛适用性与有效性。
原文摘要 · Abstract (English)
In recent years, there has been significant advancement in object detection. However, applying off-the-shelf detectors to a new domain leads to significant performance drop, caused by the domain gap. These detectors exhibit higher-variance class-conditional distributions in the target domain than that in the source domain, along with mean shift. To address this problem, we propose the Prototype Augmented Compact Features (PACF) framework to regularize the distribution of intra-class features. Specifically, we provide an in-depth theoretical analysis on the lower bound of the target features-related likelihood and derive the prototype cross entropy loss to further calibrate the distribution of target RoI features. Furthermore, a mutual regularization strategy is designed to enable the linear and prototype-based classifiers to learn from each other, promoting feature compactness while enhancing discriminability. Thanks to this PACF framework, we have obtained a more compact cross-domain feature space, within which the variance of the target features' class-conditional distributions has significantly decreased, and the class-mean shift between the two domains has also been further reduced. The results on different adaptation settings are state-of-the-art, which demonstrate the board applicability and effectiveness of the proposed approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。